pp-trustpilot

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation process utilizes npx to download and execute the @mvanhorn/printing-press package from the NPM registry. This package is owned by the skill's author.
  • [COMMAND_EXECUTION]: The skill operates by invoking the trustpilot-pp-cli binary to perform search, analysis, and data retrieval tasks related to Trustpilot reviews.
  • [DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> option and a feedback command, which enable sending tool outputs or user feedback to external HTTP endpoints. These are documented capabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Trustpilot reviews. 1. Ingestion points: reviews and search-reviews commands in SKILL.md. 2. Boundary markers: No delimiters or warnings are used to wrap ingested content. 3. Capability inventory: Execution of local CLI tool for data retrieval, analysis, and local SQLite storage. 4. Sanitization: No sanitization of the review content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 09:47 PM
Security Audit — agent-trust-hub — pp-trustpilot