seo-technical-audit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references standard SEO and development tools, including the Google Lighthouse NPM package and several Python libraries (requests, beautifulsoup4, jsonschema, and the Google API client). These are standard dependencies for the stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and analyzing external website data. Ingestion points: references/tool-commands.md and references/schema-patterns.md contain code to fetch data from URLs via curl and requests. Boundary markers: No explicit prompt boundaries or 'ignore' instructions are present in the snippets. Capability inventory: The skill uses network requests and local parsing in references/tool-commands.md. Sanitization: The skill employs structured parsing via BeautifulSoup and JSON loaders to extract specific SEO metrics.
- [CREDENTIALS_UNSAFE]: The skill includes instructions for using a service-account.json file to authenticate with Google APIs. This is a recommended security practice for handling API keys via external configuration files rather than hardcoding credentials into the logic.
Audit Metadata