limrun-xcode-bazel

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs the user to install the lim CLI tool globally using npm install --global lim. This utility is the primary interface for managing the vendor's remote build instances and simulator tunnels.\n- [COMMAND_EXECUTION]: The skill involves the execution of various shell commands including lim xcode rbe, bazelisk build, and lim ios create. These commands are standard for the intended workflow of building software and managing development environments.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes output from the lim CLI, which serves as a data ingestion surface for the agent.\n
  • Ingestion points: The agent is instructed to read the output of lim xcode rbe (to get build commands) and lim ios create (to retrieve simulator stream URLs) in the SKILL.md file.\n
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded content within the CLI output.\n
  • Capability inventory: The skill possesses the capability to execute shell commands (bazelisk, lim) and present URLs to the user based on processed data.\n
  • Sanitization: The skill does not specify any sanitization or validation logic for the CLI output before it is used by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 01:54 AM