The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes local Python scripts (bundle_analyzer.py, component_generator.py, frontend_scaffolder.py) to automate common development workflows. These scripts are designed with security in mind, incorporating path resolution logic that prevents path traversal attacks and ensures operations are confined to the intended workspace.
[EXTERNAL_DOWNLOADS]: The skill provides templates and instructions that guide users to install dependencies from the official NPM registry via standard package managers. The dependencies listed in the scaffolding logic are all common, reputable libraries in the frontend ecosystem.
[INDIRECT_PROMPT_INJECTION]: The bundle_analyzer.py script represents an ingestion surface as it reads external project files (source code and configuration). The following evidence chain applies:
Ingestion points: Reads package.json, next.config.js, and source files in src/, app/, and pages/ directories.
Boundary markers: None explicitly present in the script's raw output; reliance is placed on the agent's internal context management.
Capability inventory: The skill possesses capabilities for reading files (bundle_analyzer.py), creating directories, and writing project boilerplate (frontend_scaffolder.py, component_generator.py).
Sanitization: All included scripts implement a safe_user_path function or equivalent validation logic to ensure that file access and creation remain within the current working directory, effectively mitigating directory traversal risks.
[SAFE]: No malicious patterns, such as obfuscation, hardcoded credentials, or persistence mechanisms, were found. The skill's functionality is strictly aligned with its stated purpose of assisting in modern frontend development.

senior-frontend