q
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied questions and instructs the agent to use its existing capabilities (reading files, running commands, or searching) to verify answers based on that input.\n
- Ingestion points: User input provided via the
/qcommand.\n - Boundary markers: No specific delimiters or "ignore instructions" wrappers are defined for the interpolated user input.\n
- Capability inventory: The skill explicitly mentions reading files, running commands, and performing searches.\n
- Sanitization: No explicit sanitization or validation steps are prescribed for the input before tool execution.\n- [SAFE]: The skill consists entirely of instructional markdown and YAML metadata. There are no executable scripts, hardcoded credentials, network exfiltration attempts, or obfuscation techniques present.
Audit Metadata