review-management
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted app reviews, which creates a surface for indirect prompt injection where malicious content in a review could attempt to influence the agent.
- Ingestion points: External app reviews fetched via the user-provided App ID as described in SKILL.md.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat review content as untrusted or to ignore embedded instructions.
- Capability inventory: The agent's capabilities are limited to generating text-based analysis, metrics reports, and response drafts. It does not have access to dangerous tools like shell execution or file system writes.
- Sanitization: No sanitization or filtering of the review text is mentioned.
- [SAFE]: The skill does not contain any executable code, network exfiltration patterns, or hardcoded credentials. All recommended practices (like using SKStoreReviewController) align with standard app development guidelines.
Audit Metadata