setup-plaud-react-native
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions involve downloading and installing standard development dependencies from trusted sources, including CocoaPods via Homebrew and Expo Modules via NPX.- [COMMAND_EXECUTION]: The setup workflow requires the execution of shell commands for project configuration, filesystem operations, and native iOS builds (e.g.,
npx expo prebuild,pod install). These are necessary steps for the skill's stated purpose.- [PROMPT_INJECTION]: The skill facilitates the ingestion of external data which presents a surface for indirect prompt injection. - Ingestion points: Recording metadata and transcription text are retrieved from the Plaud platform API (
platform-us.plaud.ai) and hardware devices via Bluetooth. - Boundary markers: No specific delimiters are implemented in the provided code snippets to isolate untrusted transcription content.
- Capability inventory: The skill has access to the local file system (writing to
Documents/PlaudExports), Bluetooth hardware, and network communication (uploads to S3 and API polling). - Sanitization: The instructions do not detail specific sanitization or filtering of the transcription data before it is processed by the agent or displayed to the user.
Audit Metadata