skills/ruvnet/claude-flow/loop-worker/Gen Agent Trust Hub

loop-worker

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructs the agent to follow [LOOP_SUGGESTION] and [CRON_SUGGESTION] hints provided within tool responses. This creates an indirect prompt injection surface where a malicious or compromised tool could influence agent behavior.
  • Ingestion points: Tool responses from mcp__claude-flow__hooks_worker-dispatch (SKILL.md)
  • Boundary markers: Absent. The instructions tell the agent to follow hints directly without specifying delimiters or safety warnings for that content.
  • Capability inventory: The skill allows Bash(npx *), mcp__claude-flow__hooks_worker-dispatch, and ScheduleWakeup (SKILL.md frontmatter).
  • Sanitization: No sanitization or validation of the hints provided in tool responses is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:22 PM
Security Audit — agent-trust-hub — loop-worker