blast-radius
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of code diffs and pull requests (Step 1). This ingestion point lacks explicit boundary markers or sanitization instructions for the content being analyzed, creating a surface for indirect prompt injection if the diff contains instructions targeting the agent.
- [DYNAMIC_EXECUTION]: The skill instructs the agent to write and execute scripts or tests (Step 5) to verify the behavior of the code under review. This involves runtime generation and execution of code, which is a powerful capability that could be abused if the agent is influenced by malicious content in the diffs it is analyzing.
Audit Metadata