SG-041: Unicode Tag Block Smuggling

Severity: CRITICAL

Codepoints in U+E0000..U+E007F (invisible to renderers, read by LLM tokenizer)

Fires when

• Contains any Unicode Tag block character (U+E0000-U+E007F)
• These characters are invisible in browsers, GitHub, terminals, and IDEs but are read verbatim by the AI tokenizer, hiding instructions in what looks like blank space

Remediation

No safe remediation: a file that triggers this rule should be rejected, not patched. Read the flagged lines in the source before deciding.

Research

• https://www.pillar.security/blog/new-vulnerability-in-github-copilot-and-cursor-how-hackers-can-weaponize-code-agents
• https://embracethered.com/blog/posts/2024/hiding-and-finding-text-with-unicode-tags/