frontend-developer

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill includes a "Companion check" that explicitly instructs the agent to run local filesystem commands (ls ~/.claude/skills/ …) and report/install companion skills—an unrelated, environment-probing instruction that attempts to access local files and perform side effects outside the frontend-development scope, so it is a prompt injection.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.40). The skill is mostly safe frontend guidance but its "Companion check" tells the agent to run shell commands (ls) to inspect local skill directories and to offer installing missing skills via npx skills add, which can modify the runtime environment—so it encourages filesystem access and optional package installation though it does not request sudo, system-file edits, or user creation.