cf-info
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a PowerShell script (
cf-info.ps1) to perform its analysis. The script uses the-NoProfileflag, which is a security best practice to ensure a clean execution environment. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external configuration files provided by the user.
- Ingestion points: The script reads metadata from
Configuration.xmlat a user-defined location. - Boundary markers: Output is formatted for readability but lacks explicit delimiters to differentiate between file content and agent instructions.
- Capability inventory: The tool can read files from the filesystem and optionally write reports to a local file using the
OutFileparameter. - Sanitization: The script extracts and displays text from XML nodes without sanitization, which could lead to the agent interpreting malicious instructions embedded in the 1C metadata.
Audit Metadata