sub-agent-dispatch
Warn
Audited by Snyk on Apr 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's AGENTS.md/Tool Rules require the agent to run compose-agentsmd (and agent-ruleset.json points to github:metyatech/agent-rules@HEAD), which fetches public GitHub rule content that the agent must ingest and follow, allowing external repo content to materially change routing/behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata