llm-wiki

Warn

Audited by Snyk on Oct 29, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The workflow ingests arbitrary user-supplied URLs and web content via WebFetch and WebSearch into raw source folders without prior item selection, exposing the agent to indirect prompt injection.

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

  • Potentially malicious external URL detected (medium risk: 0.30). The script upload_wiki_ontology.py establishes an operational runtime dependency by connecting to a remote MCP server hosted at https://mcp.infranodus.com (or via INFRANODUS_MCP_URL) to execute graph upload commands. Since this remote server is a third-party project service rather than a recognized major cloud/ecosystem first-party publisher, it carries common/reputable unofficial provenance, resulting in a medium tier.

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
Oct 29, 2026, 10:16 AM
Issues
2