ah-task-creator

Warn

Audited by Snyk on Mar 9, 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 Procedure (Step 9, Researcher) explicitly instructs the subagent to "spawn parallel research tasks ... using research from the web," so the skill fetches and ingests open web content that the agent will read and use to influence planning and subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 11:16 PM