hickey-simple-made-easy
Fail
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: HIGHOBFUSCATIONPROMPT_INJECTION
Full Analysis
- [OBFUSCATION]: Large payloads of zero-width characters (U+200B, U+200C, U+200D) are appended to the main headers in SKILL.md and references/philosophy.md. This hidden content is intended to be processed by the AI agent while remaining invisible to the user.
- [PROMPT_INJECTION]: The steganographic content is positioned in markdown titles, which are high-priority context areas for agents. This is a deliberate attempt to inject instructions that could bypass safety filters or override the system prompt.
Recommendations
- AI detected serious security threats
Audit Metadata