orchestrate

Warn

Audited by Snyk on Aug 14, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). The orchestrator skill requires “research” subagents to “explore, search, [and] reading” at runtime (Step 1 research track), which can ingest outsider-authored free text depending on what specific external/public pages or sources those subagents are directed to read during the workflow.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 14, 2026, 01:53 AM
Issues
1
Security Audit — snyk — orchestrate