azure-containerregistry-py

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and acceptance criteria show it can connect to public registries (e.g., anonymous access to https://mcr.microsoft.com), download manifests/blobs (Upload and Download Artifacts) and use manifest fields (Clean Up Old Images) to decide actions like deleting images, which clearly ingests untrusted third‑party content that can influence tool behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 12:34 AM