task-delegation
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's research examples (e.g., "Research Competitive Landscape" and the "Parallel Research Delegation" agents that "Research Salesforce's B2B SaaS pricing" and "Focus on publicly available tiers") explicitly instruct agents to gather and analyze publicly available competitor information, which is untrusted third‑party web content the agent would read and interpret.
Audit Metadata