react-to-ios
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command to run a Ruby script (
add_to_xcode.rb) located within the${CLAUDE_PLUGIN_ROOT}directory. This script is used to programmatically add new files to an Xcode project, which is a required step for the skill's primary functionality. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes external source code provided by the user, which serves as an ingestion point for untrusted data.
- Ingestion points: Source files from the user-specified React codebase path (Step 1) are read and analyzed by the agent.
- Boundary markers: None; the skill lacks specific instructions or delimiters to disregard potentially malicious prompts embedded in the source code comments, strings, or data structures.
- Capability inventory: The agent can create and modify local files and execute a specific Ruby script in the shell to update project configuration.
- Sanitization: No sanitization, validation, or filtering of the ingested code content is performed prior to processing.
Audit Metadata