asking-to-understand
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes user-provided artifacts, which serves as an ingestion point for external content.
- Ingestion points: Files, codebases, and systems provided as input.
- Boundary markers: None explicitly defined to isolate artifact content from instructions.
- Capability inventory: Recommends using
ls,git, andREST GETfor verifying artifact existence. - Sanitization: No content sanitization or escaping is specified.
- [SAFE]: The skill consists of behavioral instructions for the agent and does not contain malicious code or exfiltration patterns. The use of standard tools for filesystem inspection is appropriate for the skill's purpose of artifact analysis and does not represent an elevated security risk.
Audit Metadata