weekly-review
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from git commit messages and diffs to generate a weekly report. This provides a surface for indirect prompt injection where an attacker could craft a commit message to influence the generated summary output.
- Ingestion points: Git commit history and diffs (referenced in workflow steps 2-5 of SKILL.md).
- Boundary markers: None present in the instructions.
- Capability inventory: The skill is limited to generating a text summary and does not possess capabilities for network access, file system modification, or command execution.
- Sanitization: No specific sanitization or filtering is applied to the ingested commit data.
Audit Metadata