obsidian-commander

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Ingest External Content" instructions (and README examples) explicitly show ingestion of arbitrary web pages (e.g., python scripts/ingest.py --vault . --url "https://example.com/article"), so the skill can fetch and import untrusted public/URL content that the agent is expected to read and that could influence subsequent actions.