emailworkflowskill
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill consists of markdown instructions and configuration files with no executable code or scripts.\n- [SAFE]: The instructions mandate human-in-the-loop verification and explicit approval for high-risk actions, such as DNS modifications or production email sends.\n- [NO_CODE]: No scripts, binaries, or executable logic are present within the skill files.\n- [PROMPT_INJECTION]: The skill processes external data (CRM fields, workflow exports) as intake points in references/operating-checklist.md. It provides boundary markers by separating analysis from live-system actions in SKILL.md. Capabilities include altering production automations and sending emails. Sanitization is enforced through manual review criteria and operator verification.
Audit Metadata