test-generator
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill includes robust security guidelines that prevent the agent from accessing production environments, credentials, or sensitive user data without explicit permission.\n- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection by processing external source code and documentation.\n
- Ingestion points: Processes existing code, type definitions, and test configurations from the local repository (SKILL.md).\n
- Boundary markers: The agent is instructed to verify project scripts for side effects and check Git diffs to ensure no unauthorized changes are made.\n
- Capability inventory: The skill allows the agent to run project-specific test commands and coverage analysis (SKILL.md).\n
- Sanitization: No explicit sanitization of input code content is defined, though the workflow emphasizes verification of output.
Audit Metadata