caldav-calendar
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted calendar data from external servers, which creates a surface for indirect prompt injection if events contain malicious instructions.
- Ingestion points: External calendar data is synced via vdirsyncer and read by the agent through khal list or search commands (SKILL.md).
- Boundary markers: There are no explicit delimiters or instructions provided to ensure the agent ignores prompt-like content within event titles or descriptions.
- Capability inventory: The skill possesses network capabilities for synchronization and filesystem access for managing local calendar databases.
- Sanitization: No sanitization or content filtering is implemented to validate data fetched from external providers before it enters the agent context.
Audit Metadata