peyton-jones-practical-haskell
Fail
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: HIGHOBFUSCATIONPROMPT_INJECTION
Full Analysis
- [OBFUSCATION]: The title of the skill contains a long sequence of hidden zero-width Unicode characters (U+200B, U+200C, U+200D, U+2060). This is a known technique for steganographically embedding instructions or data that are invisible to human readers but processed by the AI model.
- [PROMPT_INJECTION]: The presence of large amounts of hidden Unicode text in a skill's primary instruction file is highly characteristic of a prompt injection attempt, where the hidden content likely contains overrides to the agent's behavior or safety guidelines.
Recommendations
- AI detected serious security threats
Audit Metadata