self-subagent
Warn
Audited by Snyk on Feb 21, 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 explicitly instructs the agent to perform web searches and read third-party tool docs/GitHub READMEs to discover CLI exec modes (see SKILL.md Phase 1c and references/cli-profiles.md), which ingests untrusted public web content that can change how the agent constructs and runs subagent commands.
Audit Metadata