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
Risk Level
SAFE
Analyzed
Apr 5, 2026, 06:42 PM
Security Audit — agent-trust-hub — review-management