changelog-generator
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze git commit history, which represents an untrusted data source that could contain malicious instructions.
- Ingestion points: The agent reads git commit messages from the local repository as described in the Scans Git History section of SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate potential commands embedded within the commit messages it processes.
- Capability inventory: The skill instructions suggest reading repository history using git tools and writing formatted output to local files such as CHANGELOG.md.
- Sanitization: The instructions do not specify any validation, filtering, or escaping for the commit data before it is interpreted by the language model.
- [NO_CODE]: The skill provides markdown instructions for the AI agent to follow but does not include any accompanying scripts, binaries, or other source code files.
Audit Metadata