compound
Warn
Audited by Snyk on Jul 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). At runtime, the workflow reads candidate markdown files from other project knowledge directories via
obsidian_read_note(outsider-authored content category: body text of notes not authored by the operating user), then uses that text to draft and present a synthesized global note in the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata