skd-edit
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local PowerShell script (
scripts/skd-edit.ps1) to perform XML modifications on Data Composition Schema (DCS) files. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from existing XML templates and external text files, which could contain malicious instructions.
- Ingestion points: Content is read from the XML file at
TemplatePathand from external files when theValueargument uses the@pathshorthand. - Boundary markers: While the skill uses structured XML parsing and performs character escaping, it does not wrap ingested content in explicit delimiters or warnings to prevent the agent from interpreting data as instructions.
- Capability inventory: The skill has the permission to write modified XML content back to the file system at the user-specified
TemplatePath. - Sanitization: The scripts implement XML escaping for all values interpolated into the schema using internal helper functions to prevent XML injection.
Audit Metadata