ai-seo
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and configuration files without any executable scripts or binaries. Its operations are limited to information processing and analysis within the agent's safe environment.
- [PROMPT_INJECTION]: The skill involves analyzing external data such as competitor websites and search platform results, which introduces a surface for indirect prompt injection.
- Ingestion points: External data is ingested when the agent reviews competitor content and search engine output (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions in external content.
- Capability inventory: The skill uses analysis tools (like semrush or ahrefs) but does not involve high-risk actions like local file modification or system command execution.
- Sanitization: There is no mention of filtering or sanitizing instructions contained within the gathered external content.
- [EXTERNAL_DOWNLOADS]: The skill references reputable external documentation from Google and industry-standard SEO monitoring tools. These are informational references to well-known technology services and do not pose a security risk.
Audit Metadata