aliyun-happyhorse-r2v

Warn

Audited by Snyk on Apr 29, 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). The skill requires users to supply public HTTP/HTTPS reference_image URLs that are sent to the DashScope API and used as model inputs (see "input.media" in SKILL.md and the create_task / --reference-image handling in scripts/r2v_happyhorse.py), so arbitrary, untrusted third‑party images can be ingested and materially influence generation.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 29, 2026, 02:27 AM
Issues
1