klabnik-teaching-rust
Fail
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: HIGHOBFUSCATIONPROMPT_INJECTION
Full Analysis
- [OBFUSCATION]: The main header in
SKILL.md('# Steve Klabnik Style Guide') contains long sequences of zero-width characters (U+200B Zero Width Space, U+200C Zero Width Non-Joiner, U+200D Zero Width Joiner, and U+2060 Word Joiner). These characters are invisible to the user but are processed by the AI. - [PROMPT_INJECTION]: The hidden Unicode characters are used to embed a steganographic prompt injection attack. This method is designed to override the agent's instructions and safety filters by providing hidden commands that the AI interprets at runtime while appearing benign to human reviewers.
Recommendations
- AI detected serious security threats
Audit Metadata