knowledge-harvester

Warn

Audited by Snyk on Mar 6, 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 clones arbitrary public repositories (execSync(git clone ...) in src/lib.ts) and its SKILL.md and type definitions describe summarizing READMEs and converting external rule files from those repos into harvested knowledge, which means untrusted, user-generated third‑party content would be read and could influence downstream behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 01:09 AM