foundation-stakeholder-update
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is text transformation based on local meeting artifacts. No network exfiltration, credential harvesting, or malicious command execution patterns were identified.
- [PROMPT_INJECTION]: The skill processes untrusted input in the form of meeting notes. This surface for indirect prompt injection is addressed through the use of predefined templates and the 'Shareable update' boundary marker which separates the output message from internal generation logs.
- [SAFE]: The operational flow includes an inference summary step, ensuring that the agent's interpretation of the audience and CTA is reviewed by the user before the final artifact is produced.
Audit Metadata