mineru

Warn

Audited by Snyk on Jun 2, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the LLM context via the tool’s runtime ingestion of outsider-authored document content (e.g., a user-supplied URL or uploaded file that the user did not author) and then returning the parsed Markdown (including any embedded text) through --stdout/--to/MCP mineru_parse as readable prose; this Markdown is then fed into the agent’s LLM context by the host.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 2, 2026, 04:38 PM
Issues
1
Security Audit — snyk — mineru