prepare-changelog
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands for Git operations, including
git fetch,git log,git diff,git checkout,git commit, andgit push. These operations are essential for the skill's stated purpose of release management. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface through the ingestion of untrusted repository data.
- Ingestion points: Commit subjects extracted via
git logand file summaries fromgit diffduring the change listing phase. - Boundary markers: Absent. The skill does not employ specific delimiters or warnings to the agent when processing commit data.
- Capability inventory: Includes file system write access (
CHANGELOG.md), shell command execution (git), and GitHub API interaction via MCP (mcp_github_create_pull_request). - Sanitization: Absent. Commit content is interpolated directly into the draft changelog and pull request body without filtering or escaping.
Audit Metadata