link-audit
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use Playwright for browser-based discovery of links and images. This is a standard and legitimate application of browser automation for site auditing.
- [EXTERNAL_DOWNLOADS]: The skill performs HTTP status checks on external and internal URLs. It explicitly implements defensive measures by restricting recursive crawling to the host domain and establishing caps on the total number of pages to prevent unintended external reach or denial-of-service behavior.
- [PROMPT_INJECTION]: The instructions focus purely on the technical logic of the link audit and do not contain any patterns intended to bypass safety guardrails or override core agent instructions.
- [DATA_EXFILTRATION]: No patterns were found indicating the collection or transmission of sensitive data; the results are stored locally in a structured CSV format.
Audit Metadata