task-delegation

Warn

Audited by Snyk on Mar 5, 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 ForResearchAgents template and the parallel-research example (examples/parallel-research.md / SKILL.md) explicitly instruct agents to gather and synthesize "publicly available" competitor pricing information (Salesforce, HubSpot, Zendesk), which requires ingesting untrusted, third‑party web content that can directly influence subsequent synthesis and decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 03:44 AM