gadd-decompose

Warn

Audited by Snyk on May 17, 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 SKILL.md explicitly instructs the agent to create and re-read external GitHub child issues via the GitHub REST API (e.g., "create the child issue first... call GitHub's sub_issues endpoint" and "Before updating an existing external child Work Item, re-read it. If its body changed... stop..."), so the agent will ingest user-generated GitHub issue content that can influence whether it stops, proceeds, or how it acts.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 17, 2026, 10:01 AM
Issues
1