plan-product-launch

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of natural language instructions and organizational workflows with no executable code or scripts.
  • [SAFE]: Includes explicit safety guardrails, such as 'Never activate, publish, message, or enroll an audience without explicit authority' and requiring a 'readback of audience and content' before sending information.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies an ingestion surface for external data such as tickets and surveys. Evidence: 1. Ingestion points: SKILL.md (Workflow/Acceleration sections). 2. Boundary markers: Absent. 3. Capability inventory: Publishing and messaging capabilities mentioned. 4. Sanitization: Mitigated by mandatory user approval and readback requirements.
  • [SAFE]: External links in the Provenance section are for reference purposes and do not involve automated downloads or remote code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 03:14 AM