unix-macos-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEPERSISTENCECOMMAND_EXECUTIONCREDENTIALS_UNSAFEPRIVILEGE_ESCALATIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [PERSISTENCE]: The skill provides detailed templates and instructions for creating macOS launchd agents and daemons in
references/launchd-patterns.md. This allows for scripts to be executed persistently across reboots, user logins, or based on file system triggers.\n- [COMMAND_EXECUTION]: Extensive documentation is provided for powerful macOS-specific and Unix command-line utilities. This includes tools likeosascriptfor executing AppleScript,defaultsfor system preferences manipulation, andlaunchctlfor service management.\n- [CREDENTIALS_UNSAFE]: The reference guides inreferences/macos-commands.mddocument the use of the macOSsecurityutility to read from and write to the system Keychain (e.g.,security find-generic-password). While a standard administrative task, this provides a surface for the agent to interact with sensitive stored credentials.\n- [PRIVILEGE_ESCALATION]: The skill documents the use ofsudofor several system-level operations, such as rebuilding Spotlight indexes and flushing DNS caches. It also provides shell scripting patterns to detect if a script is running with root privileges via the$EUIDvariable.\n- [EXTERNAL_DOWNLOADS]: The skill includes instructions for using Homebrew (brew install) to download and install third-party packages and applications.\n- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect injection as it processes various system inputs that could be influenced by untrusted data. \n - Ingestion points: Use of
pbpaste(clipboard),mdfind(file metadata), reading arbitrary file contents, anddefaults read. \n - Boundary markers: The skill explicitly instructs the agent to use defensive scripting patterns like
set -euo pipefailand proper variable quoting. \n - Capability inventory: Includes full shell access, file system read/write, network operations via
curl, and persistence vialaunchd. \n - Sanitization: No specific sanitization logic is implemented in the skill body; instead, it relies on the agent following the provided defensive coding guidelines.
Audit Metadata