dotnet-enable-autocomplete
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- Persistence Mechanisms (HIGH): The skill identifies and appends code to shell startup profiles including
~/.bashrc,~/.zshrc,~/.config/fish/config.fish, and PowerShell$PROFILE. This is a persistence mechanism; any code added here executes automatically when a new shell session starts. - Data Exposure (HIGH): The skill reads the contents of shell profiles to check for existing configurations. These files are highly sensitive and frequently contain API keys, credentials, and private configuration data.
- Dynamic Execution (MEDIUM): For .NET 10+, the skill generates commands that use
evalandInvoke-Expressionto execute the output of thedotnet completions scriptcommand. This creates a dependency on the integrity of thedotnetbinary. - Indirect Prompt Injection (HIGH): The skill has a high-severity attack surface (Tier: HIGH) because it ingests untrusted data from local files and command outputs and possesses the capability to modify critical system startup files without mandatory sanitization or boundary markers.
Recommendations
- AI detected serious security threats
Audit Metadata