gtm-outreach

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No security issues were detected. The skill's operations, including reading project context and utilizing subagents for research, are consistent with its stated purpose of sales outreach generation.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it incorporates external research data into its output. This risk is minimal as the generated content is non-executable sales copy and is inherent to the skill's research function.\n
  • Ingestion points: Research results from subagent tasks focusing on personas and competitors.\n
  • Boundary markers: None identified in the prompt templates or processing logic.\n
  • Capability inventory: The skill uses 'Write' to save generated playbooks and sequences to the local projects directory.\n
  • Sanitization: No explicit sanitization or validation of the research data is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:36 AM