package-script-writer
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- Unverifiable Dependencies (MEDIUM): The skill installs the
PackageScriptWriter.Clipackage globally viadotnet tool install. This package is not from a trusted source (as defined in the security policy), posing a risk of executing unverified external code during setup. - Dynamic Execution (MEDIUM): The skill utilizes the
pswtool with the--auto-runflag, which generates a full installation script and executes it immediately. Runtime script generation and execution can be exploited if the tool or its inputs are compromised. - Indirect Prompt Injection (LOW):
- Ingestion points: User-provided values for project names (
-n), solutions (-s), and packages (-p) are interpolated into shell commands. - Boundary markers: Absent. There are no delimiters or instructions to ignore embedded commands in the input data.
- Capability inventory: The agent can execute arbitrary shell commands via the CLI tool and perform network polling via
nc. - Sanitization: Absent. The instructions do not specify validation or escaping for the input parameters, allowing for potential argument injection.
Audit Metadata