xcode-and-ios-simulator
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute various shell commands using the
limCLI, including project building (lim xcode build), simulator management (lim ios create,lim ios delete), and UI interaction (lim ios tap,lim ios type). - [EXTERNAL_DOWNLOADS]: Recommends the installation of the
@limrun/clipackage from the NPM registry. This is a vendor-provided tool required for the skill's functionality. - [DATA_EXFILTRATION]: Instructs the agent to upload build artifacts to the vendor's infrastructure at
console.limrun.comto provide preview links to the user. This is an intended feature of the remote build service. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from the local environment and the remote simulator.
- Ingestion points: Reads files from the local project directory during build operations and parses UI element data via the
lim ios element-treecommand. - Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to separate project content from the agent's instructions.
- Capability inventory: The agent has the capability to execute shell commands and write files (e.g., saving video recordings) based on logic influenced by the ingested data.
- Sanitization: Absent. There is no mention of filtering or sanitizing the output of the simulator or project files before processing.
Audit Metadata