nanoclaw-repl
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [DYNAMIC_EXECUTION]: The skill describes a /load command used for dynamic skill loading at runtime. The provided guidance mandates that these command handlers remain local and deterministic, which mitigates risks associated with arbitrary code execution.- [INDIRECT_PROMPT_INJECTION]: NanoClaw operates on persistent markdown-backed sessions. Ingesting and processing session history creates an inherent surface for indirect prompt injection if untrusted content is stored within the session files, though this is typical for persistent REPL tools.
Audit Metadata