test-automator
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze codebase artifacts and implement tests, creating a surface where adversarial instructions embedded in code could influence the agent.\n
- Ingestion points: The skill analyzes feature paths, components, services, and code diffs (SKILL.md).\n
- Boundary markers: Absent. The instructions do not define delimiters or warnings to ignore instructions that may be embedded in analyzed source code.\n
- Capability inventory: The skill operates with workspace-write permissions, allowing it to modify or create files in the environment (SKILL.md).\n
- Sanitization: Absent. No explicit validation or sanitization steps are provided for the content of the ingested files.
Audit Metadata