pp-tripadvisor

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the tripadvisor-pp-cli and tripadvisor-pp-mcp tools from the vendor's official GitHub repository (github.com/mvanhorn/printing-press-library) using go install.
  • [EXTERNAL_DOWNLOADS]: Downloads and executes an installer from the vendor's npm package (@mvanhorn/printing-press-library) via npx.
  • [DATA_EXFILTRATION]: Includes a --deliver webhook:<url> flag that allows command output to be POSTed to external URLs, provided as a documented data routing feature.
  • [DATA_EXFILTRATION]: Supports an automated feedback submission feature that sends locally stored notes to a remote server defined by the TRIPADVISOR_FEEDBACK_ENDPOINT environment variable.
  • [COMMAND_EXECUTION]: Invokes the tripadvisor-pp-cli binary to perform all search, comparison, and detail retrieval tasks.
  • [PROMPT_INJECTION]: Potential surface for indirect prompt injection through the processing of external Tripadvisor Content API data.
  • Ingestion points: Retrieves traveler reviews and photo metadata from the Tripadvisor API via reviews and digest commands.
  • Boundary markers: None explicitly defined in the skill instructions to delimit or ignore instructions within API data.
  • Capability inventory: The tool can perform network POST operations (webhooks, feedback) and write output to local files.
  • Sanitization: No specific sanitization or filtering logic is described for the user-generated review content before it is returned to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 02:18 PM
Security Audit — agent-trust-hub — pp-tripadvisor