nanoclaw-repl
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on markdown-backed sessions, which serve as an ingestion point for external data. If an attacker can influence the content of these sessions, they could attempt to inject instructions into the agent's context.
- [DYNAMIC_EXECUTION]: The
/loadcommand facilitates dynamic loading of additional skills at runtime. While the instructions emphasize keeping handlers local, the mechanism involves executing logic from external files that may not be part of the core distribution.
Audit Metadata