fdk-uat

Warn

Audited by Snyk on Jul 21, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). SKILL.md yêu cầu runtime workflow chạy curl -fsSL "$RAW/.../bootstrap.sh" | bashcurl ... "$RAW/.../policy.yaml" | grep ..., nơi $RAW trỏ tới raw content của nhánh/canary trên GitHub (outsider-authored public web text), rồi nội dung đó được đưa vào ngữ cảnh LLM thông qua việc thực thi script/harness.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 1.00). The skill fetches and executes remote install scripts at runtime (e.g., via curl -fsSL "$RAW/harness/poc-vendor-neutral/bootstrap.sh" | bash) where RAW is set to https://raw.githubusercontent.com///$CANARY (and similarly the main-URL https://raw.githubusercontent.com///<nhánh chính>), so remote content directly executes code and controls the install flow.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 21, 2026, 09:23 AM
Issues
2
Security Audit — snyk — fdk-uat