performance-audit
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Overall Assessment] (SAFE): The skill consists entirely of markdown documentation and benign JavaScript snippets meant for execution within a browser's developer context via Playwright. No evidence of obfuscation, malicious network calls, or credential theft was found.
- [Indirect Prompt Injection] (LOW): The skill instructs the agent to navigate to external URLs, which represents a potential ingestion point for indirect prompt injection. 1. Ingestion points: playwright_navigate command targets external URLs. 2. Boundary markers: No explicit boundary markers or 'ignore' instructions are provided in the guide. 3. Capability inventory: JavaScript execution in browser context, screenshotting, and network analysis. 4. Sanitization: None provided in the static markdown instructions. This risk is inherent to all web-browsing skills and does not indicate a malicious intent in this specific skill.
Audit Metadata