monitor-experiment

Warn

Audited by Snyk on Apr 7, 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 explicitly fetches and parses user-generated experiment data from Weights & Biases via wandb.Api() and references wandb.ai run URLs in Step 3.5, and those metrics and metadata are read and used by the agent to drive monitoring, interpretation, and cleanup decisions, exposing it to untrusted third‑party content that could carry indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 7, 2026, 12:24 PM
Issues
1