crontap-natural-language-schedules
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill provides a REST API fallback that uses
curlto send schedule details and environment-sourced authentication headers (ClientId,ApiKey) tohttps://api.crontap.com/v1/schedule/preview. This functionality facilitates communication with the vendor's own official infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process plain-English timing descriptions provided by users, which creates a potential surface for indirect prompt injection.
- Ingestion points: The
textfield within thepreview_scheduletool and the JSON payload of thecurlfallback inSKILL.mdaccept untrusted user input. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the user's scheduling phrases.
- Capability inventory: The skill facilitates network operations via tool calls or POST requests to
api.crontap.com. - Sanitization: Input validation is deferred to the vendor's remote tool or API endpoint.
Audit Metadata