skills/keychat-io/keychat-app/pods/Gen Agent Trust Hub

pods

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the cocoapods Ruby gem and run pod install, which fetches external dependencies from the CocoaPods repository. These are standard operations for Apple platform development.
  • [COMMAND_EXECUTION]: The skill defines allowed tools for Bash(pod *) and Bash(cd *). This allows the agent to navigate the file system and execute CocoaPods commands necessary for dependency management.
  • [PROMPT_INJECTION]: The skill instructions are clear and do not contain any patterns attempting to override agent safety guidelines or system prompts.
  • [DATA_EXPOSURE]: No sensitive file paths, hardcoded credentials, or unauthorized network exfiltration patterns were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface by processing local project files (Podfile, Podfile.lock) that may contain external content in monorepo settings.
  • Ingestion points: Reads and processes configuration from packages/app/ios/Podfile and packages/app/macos/Podfile via the pod tool.
  • Boundary markers: None present in the instructions.
  • Capability inventory: Limited to directory navigation (cd) and CocoaPods operations (pod).
  • Sanitization: Relies on the underlying pod and melos tools for command validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 06:45 PM