harness-adapters
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to interact with various local shell scripts (e.g.,
bin/fm-spawn.sh,bin/fm-send.sh,bin/fm-harness.sh,bin/fm-turnend-guard.sh) to manage the lifecycle and execution of other agents. This is an expected and documented functionality for the "firstmate" system architecture. - [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected. The instructions include safety-oriented guidelines, such as requiring verification before using new adapters and implementing "no turn ends blind" guards to ensure continuous supervision of agent activities.
Audit Metadata