seo-content-brief
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from user-provided URLs and top-ranking competitor websites to perform its core analysis. This creates an attack surface where malicious or adversarial instructions hidden within the fetched HTML or text could influence the agent's behavior during the brief generation process.
- Ingestion points: The logic defined in SKILL.md fetches target URL content (Process Step 1), homepage/sitemap context (Process Step 2), and competitor page structures (Process Step 3).
- Boundary markers: The instructions lack specific delimiting markers or safety warnings to ensure the agent treats external content as raw data rather than executable instructions.
- Capability inventory: The skill utilizes network-enabled tools to extract content from the web and suggests integration with third-party SEO tools (DataForSEO, Ahrefs) which process external data.
- Sanitization: There is no evidence of content sanitization, filtering, or validation to mitigate risks from embedded adversarial prompts in the analyzed websites.
Audit Metadata