Shortcuts Generator

Generate macOS/iOS Shortcuts by creating plist files. Use when asked to create shortcuts, automate workflows, build .shortcut files, or generate Shortcuts plists. Covers 1,155 actions (427 WF*Actions + 728 AppIntents), variable references, and control flow.

This skill appears coherent and focused on creating Shortcuts plist files, but be cautious when importing any generated .shortcut into your device: review the workflow actions and parameters before importing or running. Generated shortcuts can legitimately include powerful actions (run shell/AppleScript, delete photos, change system settings, access clipboard, make network requests, or call Apple Intelligence). Do not import shortcuts that include destructive actions (deletephotos, run shell scripts, or open arbitrary URLs) unless you understand and trust every action and referenced UUIDs. Also note the skill's SKILL.md lists allowed-tools: Write and Bash — while the skill itself doesn't request running shell commands, if your agent is permitted to run Bash it could execute local commands; restrict agent tooling or run in a safe environment if you are not comfortable with that. If you need more assurance, ask the publisher for provenance (homepage/source) or request a signed sample shortcut to audit before use.

Type: OpenClaw Skill Name: shortcuts-skill Version: 0.1.0 The skill bundle is classified as benign. Its stated purpose is to generate macOS/iOS Shortcuts by creating plist files, which is supported by the `Write` and `Bash` allowed tools (Bash is used for signing the generated shortcuts). The documentation comprehensively details the powerful capabilities of Apple Shortcuts, including actions like `runshellscript`, `downloadurl`, and system controls via AppIntents. While these documented actions could be used to create malicious shortcuts, the skill bundle itself acts as a generator/knowledge base and does not exhibit any intentional harmful behavior, prompt injection against the agent, data exfiltration, or persistence mechanisms within its own code or instructions.