Backend Python Expert
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a project initialization script (
scripts/init_fastapi_project.py) and instructions to execute it via the command line to automate project scaffolding. The script performs local file system operations including directory creation (mkdir) and file generation (write_text). - [INDIRECT_PROMPT_INJECTION]: The scaffolding script accepts user-supplied project names and directory paths as command-line arguments to determine file system write locations. This constitutes a potential surface where an agent could be manipulated to perform file operations at unintended paths if the inputs are derived from untrusted external sources.
- Ingestion points: The
project_nameand--patharguments in thescripts/init_fastapi_project.pyscript. - Boundary markers: The script does not use specific delimiters or safety warnings to separate user-provided names from file system logic.
- Capability inventory: File system write access is performed using
pathlib.Path.mkdirandpathlib.Path.write_textwithin the initialization script. - Sanitization: No explicit sanitization or path validation is performed on the user-provided arguments before they are used in file system operations.
Audit Metadata