gtm-lead-research

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a structured research assistant. It defines clear boundaries for data access (restricting to specific directories under ~/.gtm/) and explicitly forbids writing to the filesystem, committing to git, or interacting with external CRMs.
  • [SAFE]: The skill includes explicit security instructions for handling external evidence. It instructs the agent to treat credentialed or tokenized links as unsafe, and to never open or describe them, using a placeholder 'Private source withheld' instead.
  • [SAFE]: The logic for determining 'Priority' and 'Confidence' is based on evidence completeness and conflict resolution, following standard analytical best practices.
  • [SAFE]: The skill's output is strictly formatted as Markdown for the user to copy, adhering to an 'org-only' storage principle that prevents unauthorized modifications to the environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 03:45 PM
Security Audit — agent-trust-hub — gtm-lead-research