changelog
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs routine file reading of project documentation to extract versioning information. This behavior is consistent with its stated purpose and does not involve network access or sensitive system files.
- [PROMPT_INJECTION]: The skill processes content from an external file (../../CHANGELOG.md), creating a surface for indirect prompt injection. 1. Ingestion points: Reads the project's changelog file as specified in SKILL.md. 2. Boundary markers: None present; the agent is instructed to read the file content directly. 3. Capability inventory: The skill uses file reading capabilities to access documentation. 4. Sanitization: No specific sanitization is performed on the changelog content before processing.
Audit Metadata