convention
Warn
Audited by Snyk on Aug 14, 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). Outsider-authored free text can flow into runtime via the user’s
$ARGUMENTS(free-form prompt) which is ingested for mode/scoping extraction and then used to control subsequent project scanning and processing (notably inpathsmode parsing).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata