crontap-supabase-edge-function-cron

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a tool interface that ingests user-provided data such as URLs, headers, and request bodies. This presents a surface where malicious instructions could potentially be embedded in data processed by the agent.\n
  • Ingestion points: Arguments for the create_schedule tool (url, text, timezone, method, headers, body).\n
  • Boundary markers: The instructions do not specify the use of delimiters to separate untrusted data from instructions.\n
  • Capability inventory: The skill facilitates network requests to an external vendor API.\n
  • Sanitization: No explicit validation or sanitization steps are provided for the user-supplied configuration fields.\n- [COMMAND_EXECUTION]: The documentation includes a curl example for interacting with the Crontap REST API. The example follows best practices by using environment variables for sensitive credentials ($CRONTAP_CLIENT_ID, $CRONTAP_API_KEY) rather than hardcoding them.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 10:33 AM
Security Audit — agent-trust-hub — crontap-supabase-edge-function-cron