limrun-android-emulator
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the vendor's command-line interface tool via
npm install --global lim. This tool is used to interact with the Limrun cloud infrastructure. - [COMMAND_EXECUTION]: The skill provides tools to execute arbitrary shell commands within the Android emulator environment using
lim android adb-shell. It also supports the installation of Android application packages (APKs) from arbitrary remote URLs vialim android install-app <URL>. - [PRIVILEGE_ESCALATION]: The skill includes functionality to modify the emulator's trust store by adding custom Certificate Authorities (CAs) using
lim android ca add. This allows for the inspection or interception of encrypted HTTPS traffic within the emulator, which is a sensitive administrative operation. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from potentially untrusted third-party applications running on the emulator.
- Ingestion points: The agent is instructed to read the UI element hierarchy (
lim android element-tree), app-specific logs (lim android app-log), and the output of shell commands (lim android adb-shell). - Boundary markers: There are no instructions or delimiters provided to ensure the agent ignores or sanitizes instructions embedded in the data retrieved from the emulator.
- Capability inventory: The skill possesses powerful capabilities including arbitrary shell execution (
adb-shell), file system access (push-file,pull-file), and network tunneling (tunnel). - Sanitization: No validation or sanitization is performed on the data extracted from the emulator before it is processed by the agent.
Audit Metadata