30x-seo-content-brief
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface by ingesting untrusted data from external websites.
- Ingestion points: The skill uses the WebFetch tool to scrape titles, meta descriptions, and page content from the Top 10 SERP results (SKILL.md, Step 1).
- Boundary markers: No specific delimiters or safety instructions are defined to separate the fetched external content from the agent's core instructions.
- Capability inventory: The skill's capabilities are restricted to WebFetch and Read; there are no subprocess, file-write, or network-write capabilities present.
- Sanitization: The instructions do not define sanitization or validation for the content fetched from the web.
Audit Metadata