changelog-writer
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts exclusively as a text transformation tool, providing instructions for the agent to behave as a senior developer who parses commit messages and generates Markdown-formatted documentation. It contains no executable code, remote dependencies, or hidden instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data (git logs), which creates a theoretical attack surface for indirect prompt injection.
- Ingestion points: Git logs, PR lists, and commit descriptions provided by the user during interaction.
- Boundary markers: Not present. The skill does not define specific delimiters for user data.
- Capability inventory: No tools, subprocesses, network access, or file-write operations are defined in the frontmatter or body.
- Sanitization: Not present.
- Risk Assessment: Because the skill lacks any capabilities to interact with the system or external networks, the ingestion of untrusted data poses no functional security risk.
Audit Metadata