llm-evals

Fail

Audited by Snyk on Nov 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate eval-building procedure, but it recommends installing a third-party package via an unpinned npx skills@latest add command, which is mildly risky toward the user without any sign of malicious intent.

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

  • Third-party content exposure detected (medium risk: 0.30). The required workflow takes cases from production logs and bug reports (end-user and reporter free text) and feeds train traces containing that text to a fresh analyzer that proposes prompt or behavior changes, so an outsider's input can reach the agent without being selected first.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 16, 2026, 08:40 AM
Issues
2