skills/jeremylongshore/claude-code-plugins-plus-skills/feature-engineering-helper/Gen Agent Trust Hub
feature-engineering-helper
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION] (MEDIUM): The skill requests
Bash(python:*)andBash(pip:*)permissions. This allows the execution of arbitrary Python scripts and shell-based package management, providing a significant attack surface for local system manipulation. - [EXTERNAL_DOWNLOADS] (MEDIUM): Use of
Bash(pip:*)allows the agent to download and install any package from the Python Package Index (PyPI). This introduces a risk of installing malicious or compromised third-party libraries (typosquatting/dependency confusion) during the feature engineering process. - [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface detected. The skill is designed to ingest and process user-provided data and patterns for feature engineering.
- Ingestion points: User-provided feature engineering requests and data patterns described in the 'When to Use' section.
- Boundary markers: None. There are no instructions provided to the agent to distinguish between user data and instructions.
- Capability inventory:
Bash(python:*),Bash(pip:*),Write, andEdittools allow for code execution, file modification, and environment changes. - Sanitization: None detected. The skill does not specify any validation or filtering of the input data before processing it through the allowed tools.
Audit Metadata