blast-radius
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill instructions direct the agent to generate and execute local scripts or tests to verify safety hypotheses.
- Evidence: "Write a script or test that runs the real code, run it, and paste what happened."
- [COMMAND_EXECUTION]: The agent is encouraged to use shell capabilities to execute verified code snippets and analyze system behavior.
- Evidence: "You ran it. A script or test that calls the real code and fails loud if you're wrong."
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's script generation or analysis.
- Ingestion points: PR diffs, commit messages, and external library source code (SKILL.md).
- Boundary markers: None specified in the instructions.
- Capability inventory: The agent has the capability to generate and execute shell scripts, Python scripts, or test code (SKILL.md).
- Sanitization: The skill mentions stripping private information before public release but does not explicitly mention sanitizing instructions within the processed code or PR data.
Audit Metadata