CalDAV
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local command-line tools
vdirsyncerandkhalto perform calendar synchronization and management tasks. These operations are restricted to the intended scope of the tools and follow established operational patterns. - [PROMPT_INJECTION]: The skill processes external calendar data (e.g., event descriptions and titles), which constitutes a potential surface for indirect prompt injection. However, the skill's strict verification rules and narrow operational windows mitigate this risk.
- Ingestion points: External calendar events are retrieved via
vdirsyncerand read throughkhal(SKILL.md). - Boundary markers: Absent; there are no specific instructions for the agent to use delimiters when processing untrusted event content.
- Capability inventory: The skill performs file synchronization and command execution via
vdirsyncerandkhal(SKILL.md). - Sanitization: Absent; the skill does not explicitly describe sanitization procedures for event data.
Audit Metadata