python-cleanup
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs standard Python development utilities—ruff, black, mypy, isort, and autoflake—directly from the official Python Package Index (PyPI) to facilitate code analysis and formatting.
- [COMMAND_EXECUTION]: The skill utilizes various CLI tools through the shell to check, format, and fix Python source files within the project directory.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and process untrusted Python source code.
- Ingestion points: The agent is instructed to read and analyze files located in the
src/directory and the project root as part of its cleanup workflow (SKILL.md). - Boundary markers: No explicit instructions or delimiters are provided to the agent to help it differentiate between legitimate code and potentially malicious instructions embedded in comments or strings.
- Capability inventory: The skill has the capability to execute shell commands for tool invocation and to overwrite local files during the automated cleanup and modernization steps (SKILL.md).
- Sanitization: There is no logic or instruction to sanitize or filter out potentially dangerous patterns from the ingested source code before processing.
Audit Metadata