yelp-business-data

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external user-generated content (Yelp reviews and business descriptions) which could contain adversarial instructions.
  • Ingestion points: Data enters the agent's context through the /yelp/search, /yelp/business, and /yelp/reviews API endpoints described in SKILL.md.
  • Boundary markers: The skill does not implement or recommend specific delimiters or instruction-guarding prompts to isolate retrieved Yelp data from system instructions.
  • Capability inventory: The skill is restricted to performing network requests via requests.post to api.scavio.dev; no local file access or command execution capabilities were identified.
  • Sanitization: No explicit sanitization or filtering of the API-returned content is performed before presentation to the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:24 PM
Security Audit — agent-trust-hub — yelp-business-data