skills/ruvnet/ruflo/cron-schedule/Gen Agent Trust Hub

cron-schedule

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEPERSISTENCEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PERSISTENCE]: The skill provides instructions and examples for creating background workers that persist across session restarts. It specifically documents how to use scheduling tools to maintain long-running operations within the agent environment.
  • [INDIRECT_PROMPT_INJECTION]: The scheduling workflow involves passing a natural language string to the prompt argument of the worker creation tool. This establishes a surface where future executions could be influenced by malicious instructions embedded in processed data.
  • Ingestion points: The natural language prompt field within the CronCreate function call in SKILL.md.
  • Boundary markers: The instructions do not include the use of delimiters or ignore embedded instructions warnings to isolate the worker prompts.
  • Capability inventory: The skill utilizes CronCreate, CronList, CronDelete, and the mcp__plugin_ruflo-core_ruflo__hooks_worker-dispatch tool for worker management and dispatch.
  • Sanitization: No validation or sanitization mechanisms are described for the content of the scheduled prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:39 AM
Security Audit — agent-trust-hub — cron-schedule