okf-mcp

Warn

Audited by Snyk on Aug 25, 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). At startup, okf-mcp scans user-configured directories and for every discovered okf-* binary runs "<bin> schema" and parses its stdout as JSON (so outsider-authored free text embedded in a malicious skill’s schema output becomes LLM-ingested tool-input via the exposed JSON schema).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 25, 2026, 11:01 AM
Issues
1
Security Audit — snyk — okf-mcp