dag-executor

Warn

Audited by Snyk on Feb 19, 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.md explicitly instructs a subtask to "Analyze 20-30 successful SaaS landing pages" (Example Session / Task prompt), which requires ingesting open/public third-party web content whose findings drive downstream DAG decisions, exposing the agent to untrusted external content that could carry indirect prompt-injection instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 08:37 PM