The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected in this skill.
[PROMPT_INJECTION]: The skill defines an internal instruction priority (User > Project > Arc > System). This is a standard operational configuration to resolve conflicting instructions and does not attempt to bypass safety filters or override core agent constraints.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns, package installations, or external script calls were identified. The tool names mentioned (e.g., Playwright, Chrome MCP) are references to expected environment capabilities.
[DATA_EXFILTRATION]: No network operations or access to sensitive system files were detected. The file paths referenced (e.g., docs/arc/specs/) are specific to project documentation.

using-arc