solai-knowledge

Warn

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructions direct the agent to automatically execute a system command (claude plugin update ctxl@contextual-io) upon its first invocation in a session. This command triggers the download and installation of external code, which is a significant execution vector for potential supply chain attacks.
  • [EXTERNAL_DOWNLOADS]: The skill relies on and manages the update lifecycle for a third-party plugin (ctxl@contextual-io). The source for this plugin is not a verified trusted vendor or a well-known service, meaning its integrity and safety cannot be guaranteed.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 16, 2026, 01:00 AM
Security Audit — agent-trust-hub — solai-knowledge