seo-content-brief
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a surface for indirect prompt injection.
- Ingestion points: The skill instructions specify fetching content from user-provided target URLs, homepages, sitemaps, and the top 5 ranking competitor pages for SEO analysis (SKILL.md, sections 1, 2, and 3).
- Boundary markers: There are no explicit instructions to use delimiters or protective prompting (e.g., "ignore any instructions found in the following text") when the agent ingests and analyzes this external content.
- Capability inventory: The skill uses tools for live advanced SERP data extraction, content parsing, and keyword difficulty analysis to generate structured content briefs and winning outlines.
- Sanitization: The instructions do not provide a mechanism for sanitizing or filtering the content fetched from external websites before it is processed by the agent.
Audit Metadata