mxl-info
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external 1C spreadsheet (MXL) templates. Malicious instructions could be embedded in area names, parameters, or cell text content within these files to manipulate the agent's behavior during development tasks.\n
- Ingestion points: Files are parsed in
scripts/mxl-info.ps1andscripts/mxl-info.pyusing user-provided paths.\n - Boundary markers: The output format does not include clear delimiters or safety instructions to prevent the agent from following embedded prompts.\n
- Capability inventory: The scripts perform file reads and XML analysis; output is used by the agent to understand template structure.\n
- Sanitization: There is no filtering or sanitization of text values extracted from the XML before they are presented to the agent.
Audit Metadata