The Agent Skills Directory

[SAFE]: The skill's instructions and permissions are limited to the intended domain of frontend development. No malicious code patterns, obfuscation, or unauthorized data access were found.
[COMMAND_EXECUTION]: The skill uses Bash(npm:*) and Bash(npx:*) tools for routine tasks like linting and formatting. These are correctly scoped for the agent's development role.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it reads project files. Ingestion points: Documentation and source files in docs/ and apps/frontend/. Boundary markers: Absent. Capability inventory: Bash(npm:*) and Bash(npx:*). Sanitization: Absent. This is a common surface for development agents and does not indicate malicious intent.

frontend-dev