mj-notes-workflow
Warn
Audited by Snyk on Jun 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). Runtime workflow Step 2/3 ingests OUTSIDER-authored free text when processing
linknotes: it fetches external reference content (e.g.,公众号/B站/小红书) and readstitle + content 前200字into the agent’s LLM context.
MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).
- Hidden Unicode characters detected (1 type(s) found)
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W021
MEDIUMHidden or invisible Unicode characters detected (potential obfuscation or prompt injection).
Audit Metadata