hugobatista/unicode-skill-injection-poc

Proof-of-concept demonstrating invisible Unicode prompt injection in AI agent skill files. This project shows how the Unicode Tags block (U+E0000–U+E007F), zero-width characters, and bidirectional overrides can embed hidden instructions in AI agent skill files (SKILL.md) that are invisible to human reviewers but fully processed and obeyed by LLM

2Stars on the repository

3Mods indexed here, across every type

3mo agoLast push, which is what freshness is scored on

MITLicence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 3 mods

code-reviewer

01

hugobatista/unicode-skill-injection-poc

Skill Claude CodeCodex

Use when reviewing pull requests for security vulnerabilities and code quality issues.

not rated 2 3mo ago A 17 tokens original MIT

python-project-creator

02

hugobatista/unicode-skill-injection-poc

Skill Claude CodeCodex

Use when scaffolding a new Python project with hatch, ruff, pytest, and mypy configuration.

not rated 2 3mo ago A 26 tokens original MIT

security-auditor

03

hugobatista/unicode-skill-injection-poc

Skill Claude CodeCodex

Use when performing a security audit of an application following OWASP methodology.

not rated 2 3mo ago A 19 tokens original MIT