git-repo-normalize

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses standard Git commands (git rev-parse, git config, git status, git ls-files, git add, git diff) for their intended purposes. These commands are scoped to repository management and do not interact with sensitive system files or external network resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads .gitattributes and .editorconfig from the repository to identify existing policies, which is a potential surface for indirect injection if a repository contains malicious instructions in these files.
  • Ingestion points: Reads repository root files .gitattributes and .editorconfig via local file system access.
  • Boundary markers: None identified; the skill searches for specific configuration strings (e.g., * text=auto eol=lf).
  • Capability inventory: Executes Git CLI tools and performs file writes/merges to .gitattributes.
  • Sanitization: The skill looks for expected configuration values rather than interpreting file content as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 07:39 AM