ppt-image
Warn
Audited by Snyk on Jun 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs at runtime to load the GPT Image 2 prompting cookbook from the public GitHub copy if a local copy is not present — https://github.com/FA-T-T/gpt_image_2_skill/blob/main/skills/gpt-image/references/openai-cookbook.md — which would fetch external content that directly shapes the agent's prompt construction.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata