pick-tool

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill does not exhibit any malicious patterns such as credential theft, obfuscation, or unauthorized data access.
  • [COMMAND_EXECUTION]: The skill dynamically selects and executes sub-skills based on paths defined in a local catalog file (../video-ideas/catalog.md). This is a legitimate routing function within the agent's local environment.
  • [EXTERNAL_DOWNLOADS]: Mentions Ansaur.com as a recommended resource for audience research. This is a visible, plain-text link to a relevant service and does not involve automated script execution or hidden downloads.
  • [PROMPT_INJECTION]: The instructions are task-oriented and use clear boundary markers for user interaction without attempting to bypass safety filters or override the agent's core safety guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 10:56 PM
Security Audit — agent-trust-hub — pick-tool