* Tighten policy scan: hook scope, telemetry, disclosure; make blocking
policy/prompt.md — adds Part 2 (hook scope and disclosure):
- Enumerate every registered hook and read its source.
- Flag has_broad_scope_hooks when UserPromptSubmit/PreToolUse/
PostToolUse runs without a project-relevance gate, or any hook
reads user data beyond the plugin's stated scope — regardless of
whether it makes network calls.
- Flag has_undisclosed_telemetry when any hook or shipped code calls
a non-MCP host without explicit disclosure + opt-out.
- Flag description_matches_behavior=false when the install
description would not lead a reasonable user to expect the
hooks/telemetry/data-access found.
- passes=false when any of the above trip. Violations must cite the
specific hook/file and what the user wasn't told.
The bar is now "handles user data responsibly," not merely "isn't
malicious." A non-malicious plugin that observes more than its stated
purpose justifies will fail.
policy/schema.json — adds required hooks[], has_broad_scope_hooks,
has_undisclosed_telemetry, description_matches_behavior.
scan-plugins.yml:
- fail-on-findings: true (blocking — loosen later if FP rate too high)
- workflow_dispatch with scan_all input for full re-review of all
external entries
- timeout-minutes: 360 (full scan of 117 entries at ~96s each ≈ 3h)
- trigger on .github/policy/** so prompt edits get scanned
* Bump vercel SHA to test the tightened scan against it
* Adopt validate-plugins action suite; pin all external SHAs
Replaces the hand-rolled marketplace validator and bot-based bump
workflow with the shared composite actions (pinned at f846a0b).
marketplace.json:
- 62 external entries that were missing a `sha` are now pinned to
their current upstream HEAD (resolved via git ls-remote).
Workflows:
- validate-plugins.yml: invariants I1-I11 + claude plugin validate +
diff-gated clone-at-SHA validation of changed external entries.
SHA-pin (I5) is a hard error. I8/I11 stay warnings until the 15
known data issues (vendored dirs without manifests; one dotted
name) are cleaned up.
- bump-plugin-shas.yml: bot-free weekly refresh. Validates each new
SHA with claude plugin validate before opening one PR; works with
the default GITHUB_TOKEN (contents:write + pull-requests:write).
- scan-plugins.yml: Claude policy scan of changed external entries.
Non-blocking; graceful no-op if ANTHROPIC_API_KEY isn't set.
Removed:
- validate-marketplace.yml + the two TS helper scripts (superseded
by step 11/20 of validate-plugins).
validate-frontmatter.yml is kept — it's complementary (targeted
checks on agent/skill/command files for in-repo plugins).
* Remove 5 external entries that fail validation at HEAD
Step 30 (clone at pinned SHA + claude plugin validate) fails for
these at their current HEAD:
aiven Unrecognized key "logo" in plugin.json
atlassian-forge-skills skill YAML frontmatter parse error
sagemaker-ai skill YAML frontmatter parse error
speakai no plugin manifest at repo root
stagehand no plugin manifest at repo root
These can be re-added once the upstream repos are fixed.
* Wire scan-plugins to the detailed policy prompt
Adds .github/policy/prompt.md and schema.json (the full security
review rubric — malicious code, privacy, deception, safety
circumvention, exfiltration; plus network-call and software-install
flags) and points scan-plugins at it via the policy-prompt input.
With ANTHROPIC_API_KEY now configured on the repo, scan-plugins runs
the actual policy review on changed external entries instead of
no-op'ing.
* Bump scan-plugins action pin to include L11/L12 fixes
The 'Validate frontmatter' step interpolated step output directly into a
double-quoted shell string, allowing a fork PR that adds a file named
e.g. agents/$(curl ...).md to execute arbitrary commands on the runner.
- Pass the file list via env: and reference as "$FILES" so the shell
never re-evaluates the contents
- Pass PR number via env: for consistency (no ${{ }} inside run:)
- Gate the job on same-repo PRs only, since fork PRs are auto-closed by
close-external-prs.yml anyway
Impact was bounded (fork PRs get a read-only token with no secrets), but
this closes the RCE-on-runner vector entirely.
* Add auto-SHA-bump workflow for marketplace plugins
Weekly CI action that discovers stale SHA pins in marketplace.json
and opens a batched PR with updated SHAs. Adapted from the
claude-plugins-community-internal bump-plugin-shas workflow for
the single-file marketplace.json format.
- discover_bumps.py: checks 56 SHA-pinned plugins against upstream
repos, oldest-stale-first rotation, capped at 20 bumps/run
- bump-plugin-shas.yml: weekly Monday schedule + manual dispatch
with dry_run and per-plugin targeting options
Entries without SHA pins (intentionally tracking HEAD) are never
touched. Existing validate-marketplace CI runs on the resulting PR.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Fix input interpolation and add BASE_BRANCH overlay
- Pass workflow_dispatch inputs through env vars instead of direct
${{ inputs.* }} interpolation in run blocks (avoids shell injection)
- Add marketplace.json overlay from main so the workflow can be tested
via dispatch from a feature branch against main's real plugin data
Both patterns match claude-plugins-community-internal's implementation.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Use GitHub App token for PR creation
The anthropics org disables "Allow GitHub Actions to create and approve
pull requests", so GITHUB_TOKEN cannot call gh pr create. Split the
workflow: GITHUB_TOKEN pushes the branch, then the same GitHub App
used by -internal's bump workflow (app-id 2812036) creates the PR.
Prerequisite: app must be installed on this repo and the PEM secret
(CLAUDE_DIRECTORY_BOT_PRIVATE_KEY) must exist in repo settings.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Use --force-with-lease for bump branch push
Prevents push failure if the branch exists from a previous same-day
run whose PR was merged but whose branch wasn't auto-deleted.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The workflow was passing deleted files to the validation script, which
failed when trying to read them. Add --diff-filter=AMRC to only process
Added, Modified, Renamed, and Copied files.
Adds a sort check as a second step in the existing validate-marketplace
workflow. The script supports --fix to sort in place.
Sorts the existing 86 entries — pure reorder, no content change.
Previously grouped loosely by kind (LSPs first, then internal, then
external); now strictly alphabetical so insertion point is unambiguous.
* Add CI workflow to validate marketplace.json on PRs
Add a GitHub Actions workflow that validates marketplace.json is
well-formed JSON with a plugins array whenever PRs modify it. Includes:
- validate-marketplace.ts: Bun script that parses and validates the JSON
- validate-marketplace.yml: GH Actions workflow triggered on PR changes
- test-marketplace-check.js: Unit tests for the validation logic
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Strengthen marketplace validator and remove orphaned test file
- validate-marketplace.ts: check duplicate names and required fields
(name, description, source) per entry, not just valid JSON
- remove .github/workflows/test-marketplace-check.js: tested a
checkMarketplaceViolations function that doesn't exist in the PR,
and was in workflows/ instead of scripts/
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Tobin South <tobin.south@gmail.com>
The detectFileType function matched any .md file under an agents/ or
commands/ directory, including those nested inside skill content (e.g.
plugins/foo/skills/bar/agents/). These are reference docs, not plugin
agent definitions. Only validate agents/ and commands/ at the plugin
root level.
Adds a GitHub Actions workflow that validates frontmatter in agent,
skill, and command .md files changed by a PR. Checks:
- Agents: name and description are present and parseable
- Skills: description is present (required for Skill tool discovery)
- Commands: description is present and parseable
The workflow only runs when PRs touch files in agents/, skills/, or
commands/ directories, and only validates the changed files.
* Add write permissions for external PR workflow
* Use pulls.createReview instead of issues.createComment
* Revert to issues.createComment with proper permissions
