seo-audit
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it is designed to ingest and analyze data from external websites.
- Ingestion points: Untrusted data enters the agent context when it uses
web_fetchorcurlto retrieve the HTML content of user-provided URLs for auditing (as described inSKILL.md). - Boundary markers: Absent. The skill instructions do not provide specific delimiters or 'ignore' instructions to ensure the agent disregards any malicious commands that might be embedded within the retrieved HTML (e.g., in meta tags or hidden comments).
- Capability inventory: The skill's capabilities are limited to reading and reporting; it does not request or use tools for shell execution, file modification, or outbound network communication beyond the initial data fetch.
- Sanitization: There is no evidence of sanitization or validation of the fetched content before it is processed by the AI for analysis.
Audit Metadata