instruction-quality-audit

Warn

Audited by Snyk on Nov 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The required workflow reads a user-supplied instruction artifact or package path, and in package mode follows its reachable references, so outsider-authored text can enter only if the user selects a third-party artifact, which the agent does not choose or fetch.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 15, 2026, 06:53 PM
Issues
1