mxl-validate
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill parses XML templates that may contain untrusted data, creating a potential surface for indirect prompt injection where malicious instructions could be embedded in the XML to influence the agent's behavior through the validation output.
- Ingestion points: The scripts
scripts/mxl-validate.ps1(via[System.Xml.XmlDocument]::Load) andscripts/mxl-validate.py(vialxml.etree.parse) read and parse XML files from the user's workspace based on theTemplatePathargument. - Boundary markers: There are no boundary markers or explicit instructions to the agent to ignore natural language content found within the XML tags during validation.
- Capability inventory: The skill is restricted to file reading and console output. It does not perform network operations, file writes, or spawn additional subprocesses beyond its initial execution.
- Sanitization: The skill performs technical validation of XML structure and indices but does not sanitize or escape the text content of the XML before reporting it in error messages or validation results.
Audit Metadata