nemoclaw-maintainer-verify-stale
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches installation scripts and binaries from official NVIDIA domains and well-known services like Ollama. These references target trusted organizations and are documented as part of the standard setup process.
- [REMOTE_CODE_EXECUTION]: Reproduction scripts are synthesized from GitHub issue content and executed on remote Brev instances. This execution is contained within ephemeral remote sandboxes, preventing impact on the user's local system.
- [COMMAND_EXECUTION]: The skill makes extensive use of CLI tools including
gh,brev, andgitto automate the maintainer workflow. Local commands are primarily used for environment checks and metadata retrieval. - [PROMPT_INJECTION]: The skill processes untrusted data from GitHub issue bodies and comments to generate reproduction logic. It employs isolation and a comprehensive redaction pass to manage risks associated with indirect prompt injection.
- [SAFE]: Robust security controls are implemented, including a multi-layer redaction suite for tokens and PII, secure file-based propagation of API keys, and non-interactive use of privileged commands for cleanup.
Audit Metadata