technical-seo

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill requires the agent to crawl and analyze external web content, which can serve as a vector for instructions targeting the agent's behavior.
  • Ingestion points: 'SKILL.md' (Audit Workflow Step 1) and 'TECHNICAL-AUDIT.md' (Running a Technical Audit section) direct the agent to 'Crawl the target URL' and process its content.
  • Boundary markers: The skill instructions do not specify any delimiters or safety markers to isolate the content of audited pages from the agent's core instructions.
  • Capability inventory: Prompt templates in 'ON-PAGE-SEO.md' and 'TECHNICAL-AUDIT.md' ('Optimize all images', 'Add JSON-LD schema', 'Update robots.txt') imply the agent has the capability to modify the local file system.
  • Sanitization: The workflow lacks steps for sanitizing, filtering, or validating external content retrieved during crawls before it is interpreted by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 09:33 AM