blast-radius
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill instructs the agent to write and execute scripts or tests (Step 5) to verify the safety of code changes. This involves generating executable code at runtime based on the analysis context.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, including pull request diffs, commits, and library source code (Steps 1 and 3). This data could contain embedded instructions intended to manipulate the agent's behavior.
- Ingestion points: Pull request diffs, commit messages, and library source files referenced in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' commands to isolate analyzed code from agent instructions.
- Capability inventory: The skill utilizes file reading, writing, and execution capabilities to perform its analysis.
- Sanitization: The instructions advise the user to 'strip anything private before it goes anywhere public', but do not provide programmatic sanitization of ingested code.
Audit Metadata