roadmap-updater
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill performs standard documentation updates based on git history. It does not request network access, execute arbitrary commands, or access sensitive system files.
- [NO_CODE]: The skill consists exclusively of markdown instructions and does not include any executable scripts, binaries, or external library dependencies.
- [PROMPT_INJECTION]: The skill processes untrusted data from git commit messages which represents a surface for indirect prompt injection.
- Ingestion points: Git commit logs and ROADMAP.md content.
- Boundary markers: Absent.
- Capability inventory: Limited to reading and writing the local ROADMAP.md file.
- Sanitization: Not specified.
- Conclusion: The risk is minimal as the agent's actions are restricted to modifying a single documentation file within the repository context.
Audit Metadata