hegel
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user code and library documentation to generate property-based tests, which creates a surface for indirect prompt injection.\n
- Ingestion points: Project source files, existing test files, and external library documentation (SKILL.md).\n
- Boundary markers: The instructions do not provide explicit delimiters or "ignore" directives for the data being analyzed.\n
- Capability inventory: The agent is authorized to write new test files and execute commands for compilation and verification.\n
- Sanitization: There are no explicit requirements to sanitize or escape data ingested from the user's project or external sources.\n- [COMMAND_EXECUTION]: The skill instructs the agent to verify bugs by compiling and running standalone reproduction scripts (techniques/triage.md). This is a standard and necessary capability for a software testing and debugging tool.
Audit Metadata