extend-harness

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local bash scripts within the project workspace, such as scripts/generate-hook-configs.sh and evals/run.sh, to manage hook configurations and perform automated evaluations.\n- [DATA_EXPOSURE]: The skill accesses local telemetry data and debug logs stored in ~/.claude/hook-metrics/ and /tmp/ to provide performance analytics and troubleshooting functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 09:07 AM
Security Audit — agent-trust-hub — extend-harness