ai-readiness
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill defines an interface for interacting with SEO assessment tools via the Model Context Protocol (MCP). It does not include any direct shell commands, network exfiltration patterns, or unauthorized file system access.
- [NO_CODE]: The skill consists exclusively of markdown documentation and YAML configuration. No scripts (Python, JavaScript, Shell) or binaries are present, which eliminates the risk of hidden runtime execution.
- [SAFE]: The skill possesses an indirect prompt injection surface as it ingests untrusted crawl data via the
urlorreportIdparameters inSKILL.md. However, the skill lacks boundary markers or sanitization within the prompt instructions because its capabilities are strictly limited to analytical SEO reporting tools (seo_run_report,seo_list_reports) and do not include high-risk operations like file writing or subprocess execution. - [SAFE]: Analysis of the instructions and metadata revealed no attempts at prompt injection, obfuscation, or persistence. The skill operates within the boundaries of a standard reporting tool.
Audit Metadata