python-project-development
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: Analysis of the skill instructions and associated Python scripts found no malicious patterns, obfuscation, or data exfiltration attempts.
- [COMMAND_EXECUTION]: The skill defines several helper functions for running external tools like
git,uv, andruff. These functions utilize the Pythonsubprocessmodule with arguments passed as lists, effectively mitigating the risk of command injection. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection. 1. Ingestion points:
scripts/common_utils.py(safe_read) and SKILL.md (Read/Grep tools) allow reading external file content. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined. 3. Capability inventory:scripts/subprocess_helpers.py(run_cmd) and SKILL.md (Bash tool) provide shell execution capabilities. 4. Sanitization: No explicit sanitization or validation of the file contents is performed before they are processed by the agent. This is considered a low-risk inherent characteristic of development tools. - [EXTERNAL_DOWNLOADS]: The skill references official documentation and well-known development tools (e.g., Astral's Ruff and UV). These references are informational and do not involve the automated execution of untrusted remote code.
Audit Metadata