python-development-python-scaffold
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user requirements via the
$ARGUMENTSplaceholder to generate project structures, code, and shell commands. - Ingestion points: User requirements are injected via the
$ARGUMENTSvariable inSKILL.md. - Boundary markers: No delimiters or instructions to ignore embedded commands are present around the interpolated input.
- Capability inventory: The skill generates and suggests execution of shell commands (
uv init,git init,uv add,django-admin,make) and performs file-system operations (project structure creation). - Sanitization: There is no evidence of escaping or validation logic for the user-provided requirements before they are used to influence the generated shell commands or file content.
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute various shell commands to initialize projects, manage dependencies, and set up version control. While these are standard development tasks, they are triggered by user-supplied project names and requirements, creating a potential vector for command injection if the agent does not properly validate the inputs.
Audit Metadata