wiki-ingest

Warn

Audited by Snyk on May 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's required ingest workflow (Step 1: "Read the Source") explicitly reads untrusted source documents including web clippings ("markdown files from Obsidian Web Clipper"), PDFs, images and _raw/ drafts from the vault and uses their content to decide what pages to create/update and what files to delete, so third‑party/user‑generated content is ingested and can materially influence agent actions despite guidance not to follow embedded instructions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 15, 2026, 05:23 PM
Issues
1