geo-schema
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or persistence mechanisms were detected. The skill is entirely focused on its stated purpose of SEO auditing and metadata generation.
- [COMMAND_EXECUTION]: The skill mentions using standard tools like curl or WebFetch for retrieving HTML source code. This is an appropriate use of command-line tools for a web auditing function and does not involve the execution of untrusted scripts or dangerous arguments.
- [PROMPT_INJECTION]: The skill processes external HTML content, which is a potential surface for indirect prompt injection. Ingestion points: HTML content fetched via curl or WebFetch in Step 1. Boundary markers: Not explicitly defined in the instructions. Capability inventory: The skill uses text parsing and JSON-LD validation. Sanitization: No specific sanitization process is mentioned, but the focus is limited to structured data extraction. The risk is assessed as safe given the primary function of the skill.
Audit Metadata