ask-me
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains only natural language instructions for interviewing users and analyzing designs. No malicious patterns or unauthorized commands were identified.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted data from the codebase. Ingestion points: Codebase files (referenced in SKILL.md). Boundary markers: Absent. Capability inventory: Filesystem access for codebase exploration. Sanitization: Absent.
- [NO_CODE]: The skill does not include any scripts or executable code, which minimizes the potential for automated malicious behavior.
Audit Metadata