blast-radius
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests and processes untrusted external data from pull requests, commit histories, and third-party library source code. This creates a potential attack surface for indirect prompt injection if those sources contain malicious instructions.
- Ingestion points: Pull requests, commit data, and third-party library source code (SKILL.md).
- Boundary markers: None specified.
- Capability inventory: The skill encourages file reading, symbol searching, and writing/executing local scripts or tests (Step 5) to verify hypotheses.
- Sanitization: The skill includes a manual instruction for the agent to strip private data before generating public-facing output.
Audit Metadata