seo-scorecard
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
git logto analyze commit history for attributing SEO changes to specific ship dates. It also usespnpm formatto ensure the generated markdown report adheres to project styling standards. - [EXTERNAL_DOWNLOADS]: Fetches live content from the site's CMS and public web pages to verify that SEO optimizations are correctly deployed and to check visibility in AI-based search tools.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could contain malicious instructions designed to influence the agent's reporting or behavior.
- Ingestion points: Processes Google Search Console (GSC) CSV exports, GA4 report data, live CMS content, and external web page content.
- Boundary markers: Absent; there are no instructions to wrap or delimit external data to prevent the agent from following embedded instructions.
- Capability inventory: File system read/write/delete operations, Git command execution, and network fetching via tool calls.
- Sanitization: Absent; the agent is directed to read and compute statistics directly from the raw external files and site content.
Audit Metadata