review-analysis

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted data from app reviews via the get_app_reviews tool, creating a surface for indirect prompt injection.
  • Ingestion points: Untrusted app review content is fetched using get_app_reviews in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore instructions within the review text are present.
  • Capability inventory: The skill utilizes get_app_reviews, get_app_detail, and search_apps as documented in SKILL.md.
  • Sanitization: No sanitization or filtering of review content is described before the analysis is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 04:14 AM
Security Audit — agent-trust-hub — review-analysis