html-mind-map
Warn
Audited by Snyk on Jul 7, 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). SKILL.md’s required runtime flow invokes
html-skills:html-skills-listenand injectswindow.__CLAUDE_SUBMIT_URL__, after which the user’s submitted map/export data is POSTed back to that local receiver; that submitted content is outsider-authored free text (the user’s later edits/inputs) that can be included in the agent’s LLM context via the notification/submit handling path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata