claude-localize

Warn

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: MEDIUMPRIVILEGE_ESCALATIONCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PRIVILEGE_ESCALATION]: The scripts/patch_macos.py script uses osascript with administrator privileges to perform file operations in the system's /Applications directory. This triggers a native macOS password prompt for the user, granting the script root-level write access to the application bundle.
  • [COMMAND_EXECUTION]: The script executes several system commands using subprocess.run, including codesign for application signing, ditto for backups, defaults for system preferences, xattr for extended attributes, and osascript for elevated file operations.
  • [DYNAMIC_EXECUTION]: The skill dynamically modifies JavaScript files within the Claude application bundle. Specifically, the patch_whitelist function in scripts/patch_macos.py scans for a hardcoded array of supported locales and injects "zh-CN" to enable Chinese language support at the application's runtime.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests and processes various application resource files (JSON, JS) and user-supplied translation deltas while possessing significant capabilities like application modification and privilege escalation.
  • Ingestion points: Application resource files (e.g., en-US.json, index-*.js) and user-provided .work/delta-zh.json.
  • Boundary markers: None identified in the script or instructions to delimit untrusted content.
  • Capability inventory: Subprocess calls to codesign, osascript, ditto, defaults, and xattr; file writes to application bundles and configuration directories.
  • Sanitization: No explicit sanitization or validation of content read from application files or translation deltas.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 20, 2026, 12:52 PM