osmani-patterns-performance
Fail
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: HIGHOBFUSCATIONPROMPT_INJECTION
Full Analysis
- [OBFUSCATION]: The main header in
SKILL.md(# Addy Osmani Style Guide) is followed by a sequence of approximately 160 zero-width characters, including Zero-Width Space (U+200B), Zero-Width Non-Joiner (U+200C), Zero-Width Joiner (U+200D), and Word Joiner (U+2060). This content is invisible in standard text editors but is processed as data by the AI agent, representing a high-severity obfuscation technique. - [PROMPT_INJECTION]: The hidden Unicode characters encode binary data that translates to hidden instructions or identifiers (e.g., partial decoding reveals strings like 'SK1L'). This steganographic approach is used to inject unauthorized instructions into the agent's context while evading human review, which can be used to override safety guidelines or perform unintended actions.
Recommendations
- AI detected serious security threats
Audit Metadata