coach-nemoclaw-hermes
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using the
nemohermestool to manage sandboxes and delegate instructions to the Hermes agent. These operations are performed within a controlled environment defined by theNEMOCLAW_SANDBOX_NAMEvariable. - [DATA_EXFILTRATION]: The skill manages the movement of data between host and sandbox environments via
nemohermes sandbox upload/download. Potential risks are addressed through mandatory SHA-256 hash verification and file count checks to ensure integrity across boundaries. - [PROMPT_INJECTION]: The skill involves a delegation loop where Codex (primary agent) sends prompts to Hermes (sub-agent).
- Ingestion points: Instructions are passed to the sub-agent via the
$HERMES_PROMPTvariable. - Boundary markers: Explicit isolation is defined between the Codex host, Hermes sandbox, and Blender MCP environments.
- Capability inventory: Uses the
nemohermesCLI for execution, file transfer, and status monitoring. - Sanitization: Employs SHA-256 hashing for data transfers and requires independent validation of artifacts and runtime receipts before accepting sub-agent claims.
Audit Metadata