skills/zzci/skills/bkd/Gen Agent Trust Hub

bkd

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses curl and jq extensively to interact with the BKD REST API. It also includes standard git commands (git merge, git checkout, git stash) for managing project branches when in 'worktree' mode. All commands are standard for project orchestration and operate within the scope of managing the BKD system as described.
  • [DATA_EXFILTRATION]: While the skill performs network operations via curl, all requests are directed to $BKD_URL. The skill explicitly instructs the agent to ask the user for this URL if it is missing, ensuring the data destination is controlled by the user. There is no evidence of sensitive local file access or unauthorized data transmission.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 07:06 AM