skills/debug-zhuweijian/ai-research-toolkit/Confidence Check/Snyk

Confidence Check

Warn

Audited by Snyk on May 13, 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). SKILL.md explicitly requires using WebFetch/Context7 MCP to review documentation and Tavily MCP/WebSearch and GitHub to find OSS examples (Checks 3 and 4), so the agent will fetch and interpret untrusted public/web user-generated content that can change its implementation decisions.

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

May 13, 2026, 03:16 AM

Issues

1

Security Audit — snyk — Confidence Check