seo-check
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses platform-provided Playwright tools to navigate to and analyze web pages as described in its documentation. It does not attempt to access sensitive local files, environment variables, or user credentials.
- [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it ingests untrusted data from external webpage DOMs (e.g., meta tags, JSON-LD, titles). However, the instructions provide a rigid scoring framework and specific evaluation criteria for the agent, which mitigates the risk of the agent following instructions embedded in the analyzed content.
- [DATA_EXFILTRATION]: The skill performs network operations by navigating to external URLs to conduct SEO audits. This behavior is the primary intended purpose of the skill and does not involve the transfer of sensitive information to unauthorized third parties.
- [COMMAND_EXECUTION]: The skill uses JavaScript execution within the browser context via Playwright to extract metadata. This code is static, defined within the skill itself, and does not execute arbitrary commands on the host system.
Audit Metadata