build-task

Warn

Audited by Snyk on May 9, 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 explicitly fetches and ingests task content from external task references such as GitHub issues/URLs and Beads/Linear (see "Input" examples and "1. Fetch Task" / "AC source: GitHub Issue" in SKILL.md), and it parses acceptance criteria and task descriptions from those user-generated public sources to drive planning and build actions, so untrusted third-party content can influence agent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 9, 2026, 05:40 AM
Issues
1