split-main-sub-repo

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill implements security best practices by defining a default exclusion list in references/default-excludes.txt that prevents the leak of sensitive files such as .env, *.key, and *.pem during repository migration.\n- [COMMAND_EXECUTION]: The skill workflow involves executing standard Git commands such as git status, git submodule, and git remote to manage repository structures. These operations are restricted to local repository management and require interactive user confirmation as outlined in the execution flow.\n- [PROMPT_INJECTION]: The skill processes repository metadata and file content, which creates a surface for indirect prompt injection if malicious instructions are embedded in the repository being analyzed.\n
  • Ingestion points: Repository files and directory structure read during the inventory phase in SKILL.md.\n
  • Boundary markers: Absent; however, the skill requires step-by-step user confirmation for all destructive or remote operations.\n
  • Capability inventory: Subprocess execution of git commands and the scripts/merge_excludes.py script.\n
  • Sanitization: Content is not sanitized, but the skill uses an explicit exclusion list to avoid processing known sensitive or high-risk files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 02:58 AM