quantai-service

Warn

Audited by Snyk on May 19, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). Yes — the agent fetches and directly reads external task descriptions and files from the service at BASE_URL (http://54.151.204.72:8000) — e.g., /tasks, /tasks/{TASK_ID}, and /jobs/{JOB_ID}/files/strategy.cs and factor_card_default.json — and is required by the workflow to interpret that content to decide technical paths, edit/retest code, and drive subsequent actions, so untrusted third-party content can materially influence behavior.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill performs runtime requests to http://54.151.204.72:8000 (e.g., /tasks, /jobs/... and /jobs/.../files/strategy.cs) to fetch task descriptions and remote code/files that directly drive the agent's instructions and repair/retest workflow, making this external host a required runtime dependency.

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
May 19, 2026, 06:21 AM
Issues
2
Security Audit — snyk — quantai-service