nunchuk-coldcard-hsm
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on local execution of the
ckcc(Coldcard CLI) andnunchuktools to manage hardware wallet states, sign transactions, and configure security policies. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain malicious instructions.
- Ingestion points: Transaction files (PSBT), wallet descriptors, and HSM policy files (
policy.json) are processed by the agent and CLI tools. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when handling external file content.
- Capability inventory: The skill utilizes subprocess calls to
ckcc,nunchuk, andjqto perform operations on the ingested data. - Sanitization: There is no evidence of sanitization or structural validation performed on the contents of the PSBT or policy files prior to execution.
Audit Metadata