seo-local
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists solely of instructions and documentation for performing SEO audits. It does not execute unauthorized commands, modify system configurations, or access sensitive user data. References to external DataForSEO MCP tools are appropriate for the intended functional scope.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites provided by the user, representing a theoretical surface for indirect prompt injection.\n
- Ingestion points: Website content is fetched from the URL provided as an argument in the
SKILL.mdfrontmatter.\n - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the fetched website content.\n
- Capability inventory: The skill's primary capability is information extraction and report generation; it lacks tools for file system modification, privilege escalation, or arbitrary code execution.\n
- Sanitization: There are no explicit sanitization steps defined for the ingested web content, relying on the agent's baseline security model for processing external data.
Audit Metadata