image-gen

Warn

Audited by Snyk on Feb 15, 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 agent explicitly lists a WebFetch tool in agents/image-prompter.md and the skill’s docs include an example using a Google Search tool to ground image generation (Issue #5), which means it can fetch and ingest public web/search results (untrusted third‑party content) into the generation workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:07 PM