agent-id-vault
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements secure credential management using AES-256-GCM encryption and key derivation (HKDF-SHA256) based on the agent's local identity, preventing unauthorized access by other users on the same machine.
- [COMMAND_EXECUTION]: The documentation describes the use of a local Node.js CLI tool (
bin/cli.mjs) to interface with the vault, which is restricted to the skill's own directory. - [DATA_EXFILTRATION]: While the skill facilitates the use of credentials with external services like GitHub, the usage examples target well-known domains and provide explicit guidance to avoid accidental credential leakage in shell history, process lists, or chat transcripts.
Audit Metadata