geo-schema
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
curlcommand to fetch HTML from target websites for the purpose of auditing structured data. - [EXTERNAL_DOWNLOADS]: It retrieves website content from external, user-specified URLs to analyze entity graphs and validate schemas.
- [PROMPT_INJECTION]: Processing untrusted HTML from external websites creates a surface for indirect prompt injection.
- Ingestion points: External HTML content retrieved from target domains (SKILL.md).
- Boundary markers: None; the instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when handling fetched HTML.
- Capability inventory: Network access via
curland output generation to markdown files (SKILL.md). - Sanitization: No specific filtering or sanitization of the external data is described.
Audit Metadata