recipe-share-event-materials

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because it processes untrusted external data (calendar event attendees) to perform sensitive authorization actions (sharing Drive files).
  • Ingestion points: Event attendee information is fetched from Google Calendar via gws calendar events get as described in SKILL.md (Step 1).
  • Boundary markers: No delimiters or explicit warnings are provided to the agent to prevent it from being influenced by malicious content that might be embedded in attendee names or metadata.
  • Capability inventory: The skill enables the agent to grant permissions on Google Drive files using gws drive permissions create (Step 2).
  • Sanitization: There is no mechanism in the instructions to validate the attendee list or ensure that permissions are only granted to legitimate users before the action is executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 09:00 PM