template-add
Warn
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Risk of shell command injection in
SKILL.md. The command string interpolates user input directly into a PowerShell call:powershell.exe ... -ObjectName "<ObjectName>". Malicious input containing characters like"and;could execute arbitrary commands. - [PROMPT_INJECTION]: Vulnerability to indirect XML injection in
scripts/add-template.ps1. User-provided strings for names and synonyms are inserted directly into XML templates without escaping. This allows an attacker to alter the XML structure of the 1C project files. - [PROMPT_INJECTION]: Indirect injection risk surface analysis: 1. Ingestion points: User-provided arguments in
SKILL.mdand target XML files read from the local repository inscripts/add-template.ps1. 2. Boundary markers: No delimiters or specific safety instructions are used to separate untrusted input from logic. 3. Capability inventory: The skill has the ability to create directories, write new files, and modify existing XML configuration files in the source directory. 4. Sanitization: The skill lacks sanitization, validation, or escaping mechanisms for external content before interpolation into shell commands or XML documents.
Audit Metadata