openviking

Warn

Audited by Snyk on Mar 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's Python API explicitly states add_resource "Supports: local files, URLs" (references/python-api.md) and the CLI (scripts/viking.py) calls client.add_resource on an arbitrary file_path, meaning the agent can fetch and index public/untrusted URLs which it then reads/summarizes and uses for search/decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 12:27 PM