recipe-share-event-materials
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill contains no executable scripts or code, consisting entirely of markdown instructions (a recipe) for an agent to follow using pre-installed tools. No credentials, obfuscation, or persistence mechanisms were detected.- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests data from an external source (Google Calendar attendees) and uses it to perform actions (modifying Drive permissions). While this creates a potential attack surface, the impact is limited by the specific tool parameters.
- Ingestion points: Data is retrieved from Google Calendar via
gws calendar events get. - Boundary markers: No explicit markers are used to delimit the external data.
- Capability inventory: The skill uses
gws calendarandgws drivesubcommands to read and write workspace data. - Sanitization: No explicit sanitization of the input data is described in the recipe steps.
Audit Metadata