twitter-intelligence

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed exclusively for read-only research and social listening. It explicitly prohibits posting, liking, retweeting, or following on behalf of the user, which mitigates risks of unauthorized account activity.
  • [SAFE]: All external interactions are routed through a defined gateway ('SandBase'), and the skill instructs the agent to dynamically fetch tool schemas via sandbase_describe_tool, ensuring adherence to current API constraints.
  • [SAFE]: The skill uses vendor-provided tools (SandBase) and provides clear operating principles for data attribution and confidentiality.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 02:38 AM
Security Audit — agent-trust-hub — twitter-intelligence