interrogate-me
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external context from project files, which creates an attack surface for indirect prompt injection.
- Ingestion points: Instructions in SKILL.md direct the agent to scan project documents such as CLAUDE.md and project briefs for context.
- Boundary markers: Absent. The instructions do not define delimiters or provide warnings to ignore potentially malicious instructions embedded in these external sources.
- Capability inventory: This specific skill focuses on information gathering and summarizing; however, it transitions into subsequent tasks where the agent may utilize broader capabilities based on the gathered context.
- Sanitization: Absent. There is no mention of validating or filtering content from external files before processing.
Audit Metadata