tripadvisor-reviews-api

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves business descriptions and review text from an external source (Tripadvisor). This content serves as an ingestion point for untrusted data that could potentially be used to influence the agent's behavior.
  • Ingestion points: Data ingestion occurs through the /tripadvisor/location and /tripadvisor/reviews endpoints described in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or provide explicit warnings to the agent regarding the potential for malicious content within retrieved data.
  • Capability inventory: The skill allows the agent to perform network operations (HTTP POST requests) to the Scavio API.
  • Sanitization: No sanitization or filtering logic is mentioned for the retrieved external text before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill documentation refers to the scavio library for Python and Node.js and uses the api.scavio.dev endpoint. These are vendor-owned resources necessary for the skill to function.
  • [COMMAND_EXECUTION]: The skill provides standard setup instructions for installing its dependencies using pip and npm.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:24 PM
Security Audit — agent-trust-hub — tripadvisor-reviews-api