explain-ai-reply
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of natural language instructions for text analysis and does not utilize any external scripts, packages, or network capabilities.\n- [PROMPT_INJECTION]: The skill is designed to process untrusted text (AI responses), which presents a surface for indirect prompt injection. It mitigates this by instructing the agent to treat input as 'quoted data' and forbidding the execution of instructions found within the input. Ingestion point: User-pasted AI response (SKILL.md). Boundary markers: Instructions to anchor to original request and treat input as quoted data. Capability inventory: No tools or shell access. Sanitization: Instructional isolation.
Audit Metadata