ai-seo
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and prioritize context from files like
.agents/product-marketing.mdorproduct-marketing-context.md. These files are ingestion points for external data which, if containing malicious instructions, could influence the agent's behavior. - Ingestion points:
.agents/product-marketing.md,.claude/product-marketing.md,product-marketing-context.md. - Boundary markers: The instructions do not provide specific delimiters or ignore-instructions to isolate this external content.
- Capability inventory: The agent is empowered to suggest file modifications (e.g., creating
/pricing.md), perform research, and utilize connected SEO tools. - Sanitization: No sanitization or validation of the input file content is implemented.
- [EXTERNAL_DOWNLOADS]: The skill references several external resources and platforms, including Google Cloud's Open Knowledge Format (OKF) via
github.com/GoogleCloudPlatform/knowledge-catalogand various SEO monitoring services like Otterly AI and ZipTie. These references are informative for the user's workflow and do not involve automated execution of remote code.
Audit Metadata