fix(core): validate config.env, enforce version pinning, fix CI trust anchor and resolve_catalog guards (#68)

Fixes findings 2, 3, 4, 6, 7 from the issue #68 adversarial review.

- Finding 2: config.env was type-checked only. Add CATALOG_DENIED_ENV_KEYS
  (case-insensitive) for interpreter/loader-override keys (NODE_OPTIONS,
  PYTHONPATH, LD_PRELOAD, ...), apply the ASCII check and the existing
  secret-value check to env keys/values, and require env values to be
  empty or a single <PLACEHOLDER> token.

- Finding 3: version pinning was only checked by catalog_review.py (which
  never runs on the signing path per finding 1). Move enforcement into
  _validate_catalog_config: npm/uvx specs must carry @version or ==version
  (scoped names handled), docker images must have an explicit non-latest
  tag. Only the first plausible package-spec token is checked, so flags,
  <PLACEHOLDER>s, and docker subcommands/flags don't trip it. All 19 real
  catalog entries still validate clean.

- Finding 4: the CI catalog-signature gate imported bcc_core from the PR
  branch and trusted whatever CATALOG_PUBKEYS said there, so a PR changing
  both catalog.json and CATALOG_PUBKEYS (with a matching signature) went
  green. ci.yml now hardcodes the expected base64 pubkey and asserts
  bcc_core.CATALOG_PUBKEYS matches it before verifying the signature.
  NOTE: the maintainer is planning to rotate this key -- update
  EXPECTED_CATALOG_PUBKEY_B64 in ci.yml as its own reviewed change when
  that happens, never bundled with a catalog content change.

- Finding 6: resolve_catalog's anti-rollback/anti-freeze guards sat behind
  `if best_version >= 0`, so the first verified candidate was accepted
  unconditionally and the anti-freeze anchor drifted with each accepted
  candidate instead of staying fixed. The cap is now measured against the
  bundled catalog's version specifically (the trust anchor baked into the
  binary), regardless of evaluation order; bundled wins version ties; and
  a new pure `floor` parameter lets a future caller pass a persisted
  accepted-version floor.

- Finding 7: catalog id is now constrained to ^[a-z0-9][a-z0-9._-]{0,63}$.

Tests: fixed _minimal_catalog to use a pinned package (was enshrining
finding 3), rewrote the env-passthrough test to prove the validation
boundary instead of asserting env passes through unchecked, and
reordered test_resolve_catalog_rejects_absurd_version_jump so it
actually exercises the first-candidate path. Added positive/negative
tests for every new rule. Manually verified each new check by commenting
it out and confirming the guarding test goes red, then restoring it.

tests/test_core.py

@@ -1690,8 +1690,12 @@ def _minimal_catalog(version: int = 1) -> dict:
                 "official": True,
                 "setup": "basic",
                 "config": {
+                    # Pinned on purpose (issue #68 finding 3): an earlier
+                    # version of this fixture used an unpinned package and
+                    # asserted it validated clean, which enshrined the bug
+                    # instead of catching it.
                     "command": "npx",
-                    "args": ["-y", "widget-mcp"],
+                    "args": ["-y", "widget-mcp@1.0.0"],
                 },
                 "placeholders": {},
                 "env_required": {},
@@ -1952,6 +1956,213 @@ def test_validate_catalog_rejects_duplicate_ids():
     assert any("duplicate id" in p for p in problems)
 
 
+# --- validate_catalog: config.env (issue #68 finding 2) -------------------- #
+def test_validate_catalog_rejects_each_denied_env_key():
+    for key in sorted(c.CATALOG_DENIED_ENV_KEYS):
+        data = _catalog_with(
+            {"config": {"command": "npx", "args": ["-y", "widget-mcp@1.0.0"], "env": {key: ""}}}
+        )
+        problems = c.validate_catalog(data)
+        assert any("deny-list" in p for p in problems), (key, problems)
+
+
+def test_validate_catalog_rejects_denied_env_key_case_insensitively():
+    data = _catalog_with(
+        {
+            "config": {
+                "command": "npx",
+                "args": ["-y", "widget-mcp@1.0.0"],
+                "env": {"node_options": ""},
+            }
+        }
+    )
+    problems = c.validate_catalog(data)
+    assert any("deny-list" in p for p in problems)
+
+
+def test_validate_catalog_rejects_nonempty_nonplaceholder_env_value():
+    data = _catalog_with(
+        {
+            "config": {
+                "command": "npx",
+                "args": ["-y", "widget-mcp@1.0.0"],
+                "env": {"FOO_URL": "https://example.com"},
+            }
+        }
+    )
+    problems = c.validate_catalog(data)
+    assert any("empty string or a single <PLACEHOLDER>" in p for p in problems)
+
+
+def test_validate_catalog_accepts_empty_and_placeholder_env_values():
+    data = _catalog_with(
+        {
+            "config": {
+                "command": "npx",
+                "args": ["-y", "widget-mcp@1.0.0"],
+                "env": {"FOO": "", "BAR_URL": "<BAR_URL>"},
+            }
+        }
+    )
+    assert c.validate_catalog(data) == []
+
+
+def test_validate_catalog_rejects_non_ascii_env_key():
+    data = _catalog_with(
+        {
+            "config": {
+                "command": "npx",
+                "args": ["-y", "widget-mcp@1.0.0"],
+                "env": {"FÖO": ""},
+            }
+        }
+    )
+    problems = c.validate_catalog(data)
+    assert any("config.env key" in p and "ASCII" in p for p in problems)
+
+
+def test_validate_catalog_rejects_non_ascii_env_value():
+    data = _catalog_with(
+        {
+            "config": {
+                "command": "npx",
+                "args": ["-y", "widget-mcp@1.0.0"],
+                "env": {"FOO": "<Bäd>"},
+            }
+        }
+    )
+    problems = c.validate_catalog(data)
+    assert any("config.env value" in p and "ASCII" in p for p in problems)
+
+
+def test_validate_catalog_rejects_secret_looking_env_value():
+    data = _catalog_with(
+        {
+            "config": {
+                "command": "npx",
+                "args": ["-y", "widget-mcp@1.0.0"],
+                "env": {"SOME_TOKEN": "ghp_abcdef1234567890"},
+            }
+        }
+    )
+    problems = c.validate_catalog(data)
+    assert any("real secret value" in p for p in problems)
+
+
+def test_validate_catalog_rejects_node_options_env_walking_past_allowlist():
+    # The exact reproduction from issue #68 finding 2: an allowlisted
+    # `npx` command carrying NODE_OPTIONS in env, which previously passed
+    # validation and would have flowed straight into the executed
+    # subprocess via catalog_entry_to_paste_json().
+    data = _catalog_with(
+        {
+            "config": {
+                "command": "npx",
+                "args": ["-y", "widget-mcp@1.0.0"],
+                "env": {"NODE_OPTIONS": "--require /tmp/payload.js"},
+            }
+        }
+    )
+    problems = c.validate_catalog(data)
+    assert problems != []
+
+
+# --- validate_catalog: version pinning (issue #68 finding 3) --------------- #
+def test_validate_catalog_rejects_unpinned_npx_package():
+    data = _catalog_with({"config": {"command": "npx", "args": ["-y", "widget-mcp"]}})
+    problems = c.validate_catalog(data)
+    assert any("not version-pinned" in p for p in problems)
+
+
+def test_validate_catalog_rejects_unpinned_scoped_npx_package():
+    data = _catalog_with({"config": {"command": "npx", "args": ["-y", "@scope/pkg"]}})
+    problems = c.validate_catalog(data)
+    assert any("not version-pinned" in p for p in problems)
+
+
+def test_validate_catalog_accepts_pinned_scoped_npx_package():
+    data = _catalog_with({"config": {"command": "npx", "args": ["-y", "@scope/pkg@1.2.3"]}})
+    assert c.validate_catalog(data) == []
+
+
+def test_validate_catalog_rejects_unpinned_uvx_package():
+    data = _catalog_with({"config": {"command": "uvx", "args": ["some-tool"]}})
+    problems = c.validate_catalog(data)
+    assert any("not version-pinned" in p for p in problems)
+
+
+def test_validate_catalog_accepts_uvx_at_version_pin():
+    data = _catalog_with({"config": {"command": "uvx", "args": ["some-tool@1.0.0"]}})
+    assert c.validate_catalog(data) == []
+
+
+def test_validate_catalog_accepts_uvx_double_equals_pin():
+    data = _catalog_with({"config": {"command": "uvx", "args": ["some-tool==1.0.0"]}})
+    assert c.validate_catalog(data) == []
+
+
+def test_validate_catalog_rejects_docker_latest_tag():
+    data = _catalog_with({"config": {"command": "docker", "args": ["run", "some/image:latest"]}})
+    problems = c.validate_catalog(data)
+    assert any("'latest'" in p for p in problems)
+
+
+def test_validate_catalog_rejects_docker_untagged_image():
+    data = _catalog_with({"config": {"command": "docker", "args": ["run", "some/image"]}})
+    problems = c.validate_catalog(data)
+    assert any("no explicit tag" in p for p in problems)
+
+
+def test_validate_catalog_accepts_pinned_docker_image_with_flags():
+    data = _catalog_with(
+        {
+            "config": {
+                "command": "docker",
+                "args": ["run", "-i", "--rm", "-e", "SOME_TOKEN", "some/image:1.2.3"],
+            }
+        }
+    )
+    assert c.validate_catalog(data) == []
+
+
+def test_validate_catalog_does_not_pin_check_placeholders_flags_or_subcommand():
+    # A pinned uvx spec followed by flags and a <PLACEHOLDER> positional
+    # must not itself get mistaken for an unpinned package.
+    data = _catalog_with(
+        {
+            "config": {
+                "command": "uvx",
+                "args": ["mcp-server-git@2026.7.10", "--repository", "<REPO_PATH>"],
+            }
+        }
+    )
+    assert c.validate_catalog(data) == []
+
+
+# --- validate_catalog: id constraint (issue #68 finding 7) ----------------- #
+def test_validate_catalog_rejects_id_with_markup():
+    data = _catalog_with({"id": "<b>Verified</b>"})
+    problems = c.validate_catalog(data)
+    assert any("must match" in p for p in problems)
+
+
+def test_validate_catalog_rejects_id_with_uppercase():
+    data = _catalog_with({"id": "Widget"})
+    problems = c.validate_catalog(data)
+    assert any("must match" in p for p in problems)
+
+
+def test_validate_catalog_rejects_id_starting_with_dash():
+    data = _catalog_with({"id": "-widget"})
+    problems = c.validate_catalog(data)
+    assert any("must match" in p for p in problems)
+
+
+def test_validate_catalog_accepts_valid_slug_id():
+    data = _catalog_with({"id": "widget-2.thing-ok"})
+    assert c.validate_catalog(data) == []
+
+
 # --- resolve_catalog -------------------------------------------------------- #
 def test_resolve_catalog_nothing_available_returns_empty_dict():
     assert c.resolve_catalog(None, None, None) == {}
@@ -2003,13 +2214,93 @@ def test_resolve_catalog_rejects_absurd_version_jump(monkeypatch):
     pub = priv.public_key().public_bytes_raw()
     monkeypatch.setattr(c, "CATALOG_PUBKEYS", [pub])
 
-    cached = _signed(_minimal_catalog(version=5), priv)
+    # The freeze attempt goes FIRST (as `cached`), the legitimate catalog
+    # SECOND (as `remote`) -- on purpose. Putting the good catalog first
+    # (as an earlier version of this test did) never exercises the
+    # vulnerable path: the old implementation only guarded a candidate
+    # against "the best accepted so far," so whichever candidate was
+    # evaluated FIRST got in unconditionally, uncapped. Ordering the freeze
+    # attempt first is what actually proves the cap holds regardless of
+    # evaluation order.
     freeze_attempt = _signed(_minimal_catalog(version=999999), priv)
+    good = _signed(_minimal_catalog(version=5), priv)
 
-    result = c.resolve_catalog(None, cached, freeze_attempt)
+    result = c.resolve_catalog(None, freeze_attempt, good)
     assert c.catalog_version(result) == 5
 
 
+def test_resolve_catalog_caps_first_and_only_candidate(monkeypatch):
+    # issue #68 finding 6: with no bundled catalog to anchor against, a
+    # signed catalog claiming an absurd version must still be capped even
+    # when it is the ONLY candidate resolve_catalog() ever sees -- there is
+    # no "best so far" for it to be compared against, so the cap has to
+    # apply unconditionally, not "once something else has already landed."
+    priv = Ed25519PrivateKey.generate()
+    pub = priv.public_key().public_bytes_raw()
+    monkeypatch.setattr(c, "CATALOG_PUBKEYS", [pub])
+
+    freeze_attempt = _signed(_minimal_catalog(version=999999999), priv)
+
+    result = c.resolve_catalog(None, None, freeze_attempt)
+    assert result == {}
+
+
+def test_resolve_catalog_anchors_cap_to_bundled_not_a_chained_best(monkeypatch):
+    # Anti-freeze must be measured against the BUNDLED version specifically,
+    # not against "whatever the best-so-far happens to be after each
+    # candidate is accepted" -- a chained anchor lets each accepted
+    # candidate ratchet the allowed ceiling upward, so a legitimate
+    # moderate bump (cached) plus a second, much larger jump (remote) can
+    # each individually look "within _CATALOG_MAX_VERSION_JUMP of the
+    # previous one" while remote is nowhere near bundled's version.
+    priv = Ed25519PrivateKey.generate()
+    pub = priv.public_key().public_bytes_raw()
+    monkeypatch.setattr(c, "CATALOG_PUBKEYS", [pub])
+
+    bundled = _signed(_minimal_catalog(version=2), priv)
+    cached = _signed(_minimal_catalog(version=1000), priv)  # within 1000 of bundled
+    remote = _signed(_minimal_catalog(version=1900), priv)  # within 1000 of cached,
+    #                                                          NOT of bundled
+
+    result = c.resolve_catalog(bundled, cached, remote)
+    assert c.catalog_version(result) == 1000
+
+
+def test_resolve_catalog_prefers_bundled_on_version_tie(monkeypatch):
+    # issue #68 finding 6: on a tie the LAST candidate evaluated used to
+    # win, so remote silently beat bundled at equal version. Bundled --
+    # the copy frozen into the binary -- must win ties.
+    priv = Ed25519PrivateKey.generate()
+    pub = priv.public_key().public_bytes_raw()
+    monkeypatch.setattr(c, "CATALOG_PUBKEYS", [pub])
+
+    bundled_data = _minimal_catalog(version=5)
+    bundled = _signed(bundled_data, priv)
+
+    remote_data = _minimal_catalog(version=5)
+    remote_data["servers"][0]["display"] = "Remote Impostor"
+    remote = _signed(remote_data, priv)
+
+    result = c.resolve_catalog(bundled, None, remote)
+    assert c.catalog_version(result) == 5
+    assert result["servers"][0]["display"] == "Widget"
+
+
+def test_resolve_catalog_floor_rejects_below_persisted_version(monkeypatch):
+    # `floor` is a pure parameter: the caller (eventually the GUI, from
+    # persisted storage) can pass a previously-accepted version, and
+    # nothing below it may be accepted even with no bundled catalog to
+    # anchor against.
+    priv = Ed25519PrivateKey.generate()
+    pub = priv.public_key().public_bytes_raw()
+    monkeypatch.setattr(c, "CATALOG_PUBKEYS", [pub])
+
+    stale = _signed(_minimal_catalog(version=3), priv)
+
+    result = c.resolve_catalog(None, None, stale, floor=10)
+    assert result == {}
+
+
 def test_resolve_catalog_malformed_candidate_does_not_raise(monkeypatch):
     priv = Ed25519PrivateKey.generate()
     pub = priv.public_key().public_bytes_raw()
@@ -2039,15 +2330,32 @@ def test_resolve_catalog_invalid_but_signed_candidate_is_skipped(monkeypatch):
 def test_catalog_entry_to_paste_json_basic_shape():
     entry = _minimal_catalog()["servers"][0]
     result = c.catalog_entry_to_paste_json(entry)
-    assert result == {"widget": {"command": "npx", "args": ["-y", "widget-mcp"]}}
+    assert result == {"widget": {"command": "npx", "args": ["-y", "widget-mcp@1.0.0"]}}
 
 
 def test_catalog_entry_to_paste_json_includes_env_when_present():
+    # NOTE: catalog_entry_to_paste_json() is a pure shape-converter for an
+    # entry that has ALREADY passed validate_catalog() -- it is correct for
+    # it to carry env through verbatim. The bug (issue #68 finding 2) was
+    # never in this function; it was that validate_catalog() let entries
+    # with dangerous/non-placeholder env values reach this function in the
+    # first place. This test now proves that boundary explicitly: a
+    # validation-legal env value (a <PLACEHOLDER> token) survives the
+    # conversion, and a value validate_catalog() would have rejected is
+    # confirmed rejected before it ever gets here.
     entry = _minimal_catalog()["servers"][0]
     entry["config"]["env"] = {"GRAFANA_URL": "<GRAFANA_URL>"}
     result = c.catalog_entry_to_paste_json(entry)
     assert result["widget"]["env"] == {"GRAFANA_URL": "<GRAFANA_URL>"}
 
+    catalog = _minimal_catalog()
+    catalog["servers"][0]["config"]["env"] = {"GRAFANA_URL": "<GRAFANA_URL>"}
+    assert c.validate_catalog(catalog) == []
+
+    malicious = _minimal_catalog()
+    malicious["servers"][0]["config"]["env"] = {"NODE_OPTIONS": "--require /tmp/payload.js"}
+    assert c.validate_catalog(malicious) != []
+
 
 def test_config_has_unfilled_placeholders_true_for_token():
     cfg = {"command": "npx", "args": ["-y", "server", "<ALLOWED_DIR>"]}