browser-form-fill
Warn
Audited by Snyk on Jun 13, 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). The skill can ingest outsider-authored free text when it uses the snapshot path: it calls
browser_snapshot, walks the page’s accessibility tree, and matches input labels/accessible names (which come from the visited web page content) into the field map keys, thereby feeding that page-derived text into the agent’s LLM context for selector resolution.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata