nav-brief
Warn
Audited by Snyk on Jul 30, 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). In SKILL.md the brief is rendered only when an injected
NAV-BRIEFreminder block is present in the current turn’s context (triggered byhooks/nav_brief.pyonUserPromptSubmit), meaning the agent consumes the user’s submitted prompt text directly but does not read arbitrary outsider-authored external content sources.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata