seo-content-brief
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes content from external, untrusted sources including target websites and competitor pages. This creates a vulnerability surface where malicious instructions embedded in external content could potentially influence the agent's research and output.
- Ingestion points: Fetches content from user-provided target URLs, the site's homepage, and XML sitemaps to understand business context; also analyzes the top 5 ranking pages for target keywords to identify gaps (
SKILL.md). - Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the external content were identified.
- Capability inventory: The skill's capabilities are focused on research and content generation. No access to sensitive system files, shell execution, or persistence mechanisms was detected.
- Sanitization: The skill does not define specific sanitization or filtering logic for the data retrieved from external sources before it is processed.
- [DATA_EXPOSURE_EXFILTRATION]: The skill performs network operations to fetch research data and integrates with established SEO services.
- Fetches sitemap and webpage content to inform competitive analysis and site structure mapping.
- Utilizes DataForSEO and Ahrefs MCP tools for keyword volume, difficulty, and organic search data.
Audit Metadata