warpctrl
Warn
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands to manage terminal windows, tabs, and sessions via the warpctrl utility. This includes a setup workflow that attempts to create a symlink in /usr/local/bin/. If the agent encounters permission issues, it is instructed to use osascript to request administrator privileges from the user. This privilege escalation is strictly gated by the ask_user_question tool to ensure human oversight.\n- [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface when processing user requests to manipulate the terminal's input buffer.\n
- Ingestion points: Data enters the context via the input insert and input replace command sequences in SKILL.md.\n
- Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore potentially malicious content within the text to be inserted.\n
- Capability inventory: The skill can perform system-level operations including command execution via warpctrl and file system modification via ln and osascript in SKILL.md.\n
- Sanitization: The skill lacks explicit sanitization for the content placed in the terminal buffer. However, it incorporates a safety limitation that prevents the staged text from being automatically submitted or executed by the terminal.
Audit Metadata