gtm-content

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for B2B content generation and operates strictly on local data. It reads business context from JSON files in the data/gtm/ directory and writes generated content back to the same location.
  • [DATA_INGESTION]: The skill ingests data from external sources including $ARGUMENTS, CLAUDE.md, and several JSON files (messaging_framework.json, icp_profiles.json, etc.). While this presents a surface for indirect prompt injection, the skill lacks dangerous capabilities such as network access or arbitrary command execution, rendering the risk negligible.
  • [FILE_SYSTEM_OPERATIONS]: The skill performs read and write operations limited to the project's local data/gtm/ directory. This is consistent with its stated purpose of managing and persisting GTM (Go-To-Market) content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 10:41 AM
Security Audit — agent-trust-hub — gtm-content