obsidian-second-brain

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

• Third-party content exposure detected (low risk: 0.10). The agent ingests external web content, URLs, PDFs, X posts, YouTube transcripts, and RSS feeds via tools like WebFetch and research commands during ingestion workflows without prior selection or sanitization.

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

• Potentially malicious external URL detected (medium risk: 0.30). An operational dependency exists because the skill instructs runtime installation via npx skills add https://github.com/akillness/jeo-skills and cloning from https://github.com/akillness/obsidian-second-brain, where the publisher provenance for akillness is an individual-owned repository rather than a recognized vendor or authenticated first-party source, making it a common/reputable unofficial operational dependency (medium tier).