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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata