axe-simulator-control
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires installing a third-party tool using
brew tap cameroncooke/axe && brew install axe. This downloads and executes code from an unverified external source via Homebrew.\n- [COMMAND_EXECUTION]: The skill executes multiple shell commands to control the iOS Simulator, includingaxe tap,axe type,axe gesture, andaxe record-video. These commands interact directly with the local system's simulator environment for automation.\n- [INDIRECT_PROMPT_INJECTION]: The skill usesaxe describe-uito extract the accessibility tree of the target iOS application. This content is then processed by the agent to determine interaction coordinates. If the target application displays malicious or adversarial text within its UI (e.g., in accessibility labels or text fields), it could influence the agent's behavior.\n - Ingestion points: UI tree data extracted via
axe describe-uias described inSKILL.md.\n - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content within the UI tree data.\n
- Capability inventory: Shell command execution (via the
axetool), file system writing (for screenshots and video recordings), and UI element inspection.\n - Sanitization: No explicit sanitization or filtering is mentioned for the UI tree content before it is processed by the agent.
Audit Metadata