Software Engineer

• Verdict: Review
• Confidence: High
• Analyzed: May 10, 2026, 4:21 PM
• Findings: 0
• Version: 1.0.0

Overview

Prompt-injection indicators were detected in the submitted artifacts (unicode-control-chars); human review is required before treating this skill as clean.

This skill appears safe to install as a coding-style assistant. It may guide the agent to inspect and edit files in the current project when you ask for engineering work, so review generated code and keep normal workspace permissions appropriately scoped. ClawScan detected prompt-injection indicators (unicode-control-chars), so this skill requires review even though the model response was benign.