agentic-workspace
Warn
Audited by Snyk on Mar 2, 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 defines a Research agent (SKILL.md and references/agent-template.md) that uses tools like "search" and "fetch" to ingest external web/GitHub/npm/docs content and then supplies sourced findings that drive handoffs and orchestrator/plan decisions, which exposes the agent to untrusted third‑party content that could carry indirect prompt injection.
Audit Metadata