crontap-replace-vercel-cron
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external configuration data which could contain malicious instructions.
- Ingestion points: The agent is directed to read the
vercel.jsonfile to extract cron schedules. - Boundary markers: No specific delimiters or instructions to ignore nested commands are provided for the ingested data.
- Capability inventory: The skill utilizes tools for schedule management (
create_schedule,pause_schedule,resume_schedule). - Sanitization: No explicit sanitization or validation of the ingested cron expressions or paths is described.
- [EXTERNAL_DOWNLOADS]: The skill includes code examples for interacting with
api.crontap.comviacurl. This is a vendor-owned resource for the Crontap service and is used for legitimate API interactions.
Audit Metadata