calendly
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
npxto execute the@useclawlink/clitool for authentication and management tasks. - [EXTERNAL_DOWNLOADS]: The skill installs the
@useclawlink/clipackage from the NPM registry at runtime usingnpx. This is a vendor-specific tool belonging to the skill author's organization. - [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from external Calendly accounts, which could contain instructions intended to influence the agent's behavior. 1. Ingestion points: Calendly event data, invitee lists, and availability schedules retrieved through CLI commands in SKILL.md. 2. Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands in the processed data. 3. Capability inventory: The skill utilizes subprocess execution via shell commands (
npx). 4. Sanitization: There is no evidence of sanitization or validation of the data retrieved from the Calendly service.
Audit Metadata