poly-pizza-api

Warn

Audited by Snyk on Apr 21, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to call the public Poly Pizza API (https://api.poly.pizza/v1/ search, model, and popular endpoints) and to read model metadata fields (Title, Description, Creator/PURL, Tags) and CDN Download URLs returned by user-contributed models, so untrusted, user-generated content from the open web is ingested and used to choose, name, attribute, and download assets—allowing those fields to influence agent decisions and subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 21, 2026, 08:25 PM
Issues
1