tensorart-generate

Warn

Audited by Snyk on Apr 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: 0.80). The skill explicitly fetches tool metadata from the external TensorArt/Tusi OpenAPI (see SKILL.md Step 2 and scripts/list_tools.py calling openapi.tensor.art) and instructs the agent to read and analyze each tool's name/description/tags to choose actions (and it also downloads result URLs via scripts/download_result.py), so untrusted third-party content is ingested and can directly influence tool selection and subsequent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 21, 2026, 12:33 PM
Issues
1