playbook-creative-ideas

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The documentation provides shell commands for creating and running automation workflows using the clay CLI.
  • [EXTERNAL_DOWNLOADS]: The workflow retrieves company data from various external enrichment providers and APIs to populate the prompt context.
  • [SAFE]: The skill implements a verification step that requires the AI to quote its source text as a verifiable substring. This programmatic check ensures the output is grounded in the provided evidence and serves as a safeguard against the model following unauthorized instructions or inventing details.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 02:36 PM
Security Audit — agent-trust-hub — playbook-creative-ideas