learn-loop
Warn
Audited by Snyk on Aug 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Required runtime reads outsider-authored free text from user-provided
$ARGUMENTS(used to name/open the capture note) and, more importantly, from files/PDFs/screenshots and inbox content that the user has “scattered-captured” into"$VAULT/00-inbox/"(which can include attacker-injected text), plus it can perform WebSearch/WebFetch when no local material is found.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata