drift-analysis

Warn

Audited by Snyk on Feb 20, 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.md explicitly describes collectors.js scanning GitHub state and parsing documentation files (see "GitHub Data" and "Documentation Data" in the Data Collection section) and the plan-synthesizer then reads that collected, user-generated content to drive cross-referencing and recommendations, which could allow untrusted third-party content to influence agent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 02:07 AM