sanity-gsc

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADS
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill requires the installation of the @pagebridge/sanity-plugin and other dependencies from the PageBridge-IO organization. These are unverifiable packages from a source not listed in the trusted external sources, presenting a potential supply-chain risk.
  • CREDENTIALS_UNSAFE (SAFE): The skill handles sensitive Google Service Account and Sanity credentials. It adheres to security best practices by using environment variable placeholders and a .env configuration pattern rather than hardcoding secrets.
  • INDIRECT_PROMPT_INJECTION (LOW): The skill ingests untrusted data from GSC and Sanity APIs. (1) Ingestion points: Performance metrics and document content entering via GSC and Sanity. (2) Boundary markers: Absent in instructions. (3) Capability inventory: Network API communication, local database writes, and CMS writes. (4) Sanitization: No explicit validation or sanitization of external data is described in the documentation.
  • COMMAND_EXECUTION (SAFE): Standard CLI operations (pnpm sync, pnpm list-sites) are used as the primary interface. No malicious or obfuscated command patterns were detected.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:35 PM