agent-tuning

Warn

Audited by Snyk on Feb 26, 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 using WebSearch and links to external public sites (e.g., biggerpockets.com and ElevenLabs docs) in the "Resources & References" / "Research & Learning" sections, which means the agent may fetch and act on open/public web content that can influence prompt engineering and agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 26, 2026, 02:36 PM