hook-persistence
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of documentation and pseudocode for a state management protocol. No executable scripts, binaries, or shell commands are provided.
- [DATA_EXFILTRATION]: The described protocol manages state via local JSON files in the .chipset/state/hooks/ directory. No access to sensitive user data or external network communication was identified.
- [PROMPT_INJECTION]: The documentation focuses on system design and does not contain malicious instructions intended to subvert AI safety or override system prompts.
Audit Metadata