gws-workflow-meeting-prep

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: the skill retrieves meeting agendas and attendee information from an external calendar. this data is considered untrusted as it can be modified by third parties to include adversarial instructions intended to influence the agent's behavior. while this is a standard risk for skills processing external communication data, users should be aware that the agent may be misled by malicious content within meeting descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:42 PM
Security Audit — agent-trust-hub — gws-workflow-meeting-prep