gtm-x-outreach
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external content (X/Twitter posts) to generate hooks for personalized messages. This potential surface for indirect injection is mitigated by the requirement for operator approval before any message is sent.
- [COMMAND_EXECUTION]: The skill uses local shell commands (test, curl) to verify the existence of local configuration files and the status of the local MCP server (localhost).
Audit Metadata