gtm-icp
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill contains instructions for users to install a required dependency and references a routine check for newer releases from the author's repository (
eliasstravik/gtm-skills).\n- [COMMAND_EXECUTION]: The skill provides a command-line instruction (npx skills add eliasstravik/gtm-skills -s gtm-workspace -y) for users to manually resolve environment requirements.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads data from user input, existing ICP files, and workflow definitions to generate new documentation, creating an attack surface for instructions embedded in those sources.\n - Ingestion points: User requests, existing ICP files (
icps/), and workflow scripts (workflows/*.ts).\n - Boundary markers: Not explicitly specified in the skill instructions.\n
- Capability inventory: File system read/write access and Git operations including commit and push.\n
- Sanitization: No specific input validation or escaping mechanisms are described in the procedure.
Audit Metadata