changelog-generator
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and summarize git commit history, which can contain untrusted data provided by third-party contributors. These commit messages could potentially contain instructions designed to bypass agent constraints or inject malicious content into the generated changelog.
- Ingestion points: Git commit history and local
CHANGELOG_STYLE.mdfiles. - Boundary markers: Absent. The instructions do not include specific delimiters or warnings to ignore instructions embedded within the commits.
- Capability inventory: The skill leverages tool-based access to the filesystem/git history to read logs and outputs formatted markdown. It does not perform network operations or privileged command execution.
- Sanitization: None specified.
- [NO_CODE]: The skill consists entirely of descriptive markdown and frontmatter configuration without any bundled scripts, binaries, or automated installers.
Audit Metadata