restraint
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's function of reviewing and modifying project files creates a surface where instructions hidden in the code could influence the agent.\n
- Ingestion points: Source code, UI definitions, and dependencies (SKILL.md).\n
- Boundary markers: No specific delimiters are used to isolate the skill's instructions.\n
- Capability inventory: The agent is empowered to delete code, variables, and dependencies (SKILL.md).\n
- Sanitization: No sanitization of the analyzed content is specified.
Audit Metadata