rea-changelog-update
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git history, pull request descriptions, and commit messages to generate release notes, creating a surface for potential instruction injection via commit messages.
- Ingestion points: The skill fetches repository history, tags, and GitHub-associated PR metadata (titles, bodies, merge commits) using
scripts/release-notes.mjs. - Boundary markers: No explicit boundary markers or "ignore embedded instructions" warnings are provided in the prompt to separate ingested commit data from the agent's core instructions.
- Capability inventory: The skill executes local scripts via
node, writes to the/tmpdirectory, and modifies Pull Request bodies using theghCLI tool. - Sanitization: There are no specified sanitization or filtering steps for the text retrieved from commit messages or PR bodies before it is processed for summarization.
- [COMMAND_EXECUTION]: The skill relies on the execution of repository-local scripts (
scripts/release-notes.mjs) and the GitHub CLI (gh) to perform its primary functions, including inventory management, rendering, and PR updates.
Audit Metadata