improve-aeo-geo
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection due to its core functionality of reading and writing to a user-controlled codebase. If the analyzed codebase contains malicious instructions disguised as code or content, the agent might inadvertently follow them while performing its audit.
- Ingestion points: The skill is instructed to discover and analyze the entire website stack, including layout files, document components, page content (MDX/MD), and configuration files (robots.txt, functions.php, etc.).
- Boundary markers: The provided instructions do not specify any delimiters or safety warnings to ensure the agent ignores instructions found within the audited files.
- Capability inventory: The agent is authorized to perform targeted file system modifications across the project root to implement SEO and GEO improvements, including creating new files (llms.txt) and editing existing ones (layouts, robots.txt, metadata).
- Sanitization: There is no defined process for sanitizing or validating the content read from the codebase before the agent processes it or generates code changes based on it.
Audit Metadata