blueprint-promote

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's operations are confined to the project's internal configuration directory (.claude/). It does not access sensitive system paths or credentials.\n- [COMMAND_EXECUTION]: The skill uses the Bash tool for a simple existence check (test -f) to verify rule files before processing. This is a standard check that does not involve privileged commands or dangerous shell operations.\n- [SAFE]: A user confirmation step (AskUserQuestion) is implemented before the manifest is updated, ensuring that modifications are transparent and authorized by the user.\n- [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or remote code execution was found. The skill's functionality is consistent with its stated purpose of artifact preservation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 01:17 AM