changelog-generator
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes git commit messages, which are an external data source that could potentially contain malicious instructions if the repository has untrusted contributors.
- Ingestion points: Git commit history and messages processed during the generation phase.
- Boundary markers: The instructions do not define specific delimiters to separate the data (commit messages) from the agent's task instructions.
- Capability inventory: The skill uses tools to read git history and is encouraged to write the final output to the local file system (e.g., CHANGELOG.md).
- Sanitization: The skill instructions do not specify any sanitization or filtering logic for the commit message content before processing.
- [SAFE]: The skill contains no executable scripts, remote code downloads, or obfuscation techniques. All instructions provided are consistent with the stated purpose of generating changelogs and follow standard software development practices.
Audit Metadata