stakeholder-update
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for generating text-based status updates and does not execute untrusted code or access sensitive system credentials. Its execution model is strictly human-in-the-loop for any outward-facing actions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes project data and user-provided metrics to generate reports. The potential for indirect prompt injection via these data sources is addressed through mandatory verification; all generated updates must be shown to the human verbatim and explicitly approved before being sent to external communication channels like Slack or Email.
Audit Metadata