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.txtthat prevents the leak of sensitive files such as.env,*.key, and*.pemduring repository migration.\n- [COMMAND_EXECUTION]: The skill workflow involves executing standard Git commands such asgit status,git submodule, andgit remoteto 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
gitcommands and thescripts/merge_excludes.pyscript.\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