review-response-writer
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists solely of markdown text, templates, and guidelines. No code, scripts, or network operations are included.\n- [PROMPT_INJECTION]: The skill handles untrusted external data (App Store reviews), creating a potential surface for indirect prompt injection.\n
- Ingestion points: The skill is designed to process user-provided review text as described in the templates and response strategies.\n
- Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted review content from the agent's logic.\n
- Capability inventory: The skill configuration allows access to filesystem tools (
Read,Write,Edit,Glob,Grep) which could be targeted by instructions embedded in a review.\n - Sanitization: No mechanisms for sanitizing or filtering external review content are implemented.
Audit Metadata