figma-to-code

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The companion-check section instructs the agent to run local shell commands (ls) and suggest installing packages via npx, which is a meta, system-level action unrelated to the Figma-to-Code purpose and could expose or modify the local environment.

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

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The skill instructs the agent to inspect local hidden skill directories (ls of ~/.claude/..., etc.) and to offer installing missing companions via an npx command, which encourages reading local filesystem state and potentially modifying the environment by installing packages—an action that can change the machine state and execute remote code.