NYC

dag-skill-registry

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 registry's loadRegistry function reads and parses SKILL.md files from provided skillPaths and the doc explicitly lists "community registries" as a source, so it ingests user-contributed/untrusted skill files that the agent will read and interpret.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:24 PM