obsidian-manager
Warn
Audited by Snyk on Feb 16, 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 explicitly ingests and searches external user-generated/public content — e.g., Readwise/ (Articles, Books, Tweets) and Snipd/ (podcast transcripts) via search-readwise.py and search-snipd.py and guidance in "When to Read from Vault" — which the agent is expected to read and interpret.
Audit Metadata