clickhelp
Warn
Audited by Snyk on May 2, 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). This skill uses Membrane actions that fetch and return ClickHelp portal content (e.g., "Search Portal" and "Get Topic returns information on a single topic including its HTML content" in SKILL.md), which means the agent will read/interpret third-party (potentially user-generated or public) HTML/topics as part of its workflow and those documents could contain instructions that influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata