crontap-natural-language-schedules

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill resolves schedule timing by sending requests to the official vendor API at api.crontap.com.
  • [CREDENTIALS_UNSAFE]: Instructions for the REST API fallback correctly guide the use of environment variables ($CRONTAP_CLIENT_ID and $CRONTAP_API_KEY) to manage authentication tokens, avoiding the risks associated with hardcoding secrets.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process natural language descriptions provided by users.
  • Ingestion points: User-provided timing text processed by the preview_schedule tool and the REST API fallback (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters for separating user input from the surrounding prompt.
  • Capability inventory: The skill is limited to performing schedule previews via tool calls and network requests to vendor-controlled endpoints (SKILL.md).
  • Sanitization: There is no mention of input sanitization or validation logic for the user-supplied timing phrases.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 10:34 AM
Security Audit — agent-trust-hub — crontap-natural-language-schedules