blast-radius
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of code diffs and repository source files. A malicious diff could contain instructions designed to influence the agent's analysis or the scripts it generates.
- Ingestion points: Code diffs and repository source files (SKILL.md, Workflow steps 1 and 3).
- Boundary markers: Absent; the skill does not define specific delimiters for analyzed content.
- Capability inventory: The agent is instructed to write and execute scripts or tests (SKILL.md, Workflow step 5).
- Sanitization: Absent; no explicit validation of the code before execution is mentioned.
- [DYNAMIC_EXECUTION]: The skill instructs the agent to generate and execute scripts that run production code at runtime to verify safety claims (SKILL.md, Workflow step 5).
- [COMMAND_EXECUTION]: The workflow involves running test scripts and capturing their output, which requires shell command execution capabilities.
Audit Metadata