epf-validate
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external XML source files for 1C:Enterprise objects. These files represent an ingestion point for untrusted data. A maliciously crafted XML file could contain instructions intended to influence the agent's behavior when it interprets the validation results. Ingestion points: XML files at
ObjectPathare parsed inscripts/epf-validate.ps1andscripts/epf-validate.py. Boundary markers: The validation output uses clear structural prefixes ([OK], [ERROR], [WARN]). Capability inventory: The skill can read files and write logs to a user-specifiedOutFile. Sanitization: Standard XML parsing libraries are used, ensuring structural integrity though not sanitizing natural language content within the XML nodes. - [COMMAND_EXECUTION]: The skill executes local PowerShell and Python scripts to perform the validation logic. These scripts are contained within the skill's own directory and do not attempt to execute arbitrary or remote commands.
Audit Metadata