changelog-generator
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process git commit messages, which are untrusted external inputs.
- Ingestion points: Git commit history accessed via git tools.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined in the instructions to isolate commit content from agent instructions.
- Capability inventory: The skill involves reading git logs and writing to the local file system (e.g., CHANGELOG.md).
- Sanitization: No explicit sanitization or filtering of commit messages is defined to prevent instructions within commits from being interpreted by the agent.
Audit Metadata