onesignal-mobile-sdk-setup
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill instructions include an 'Anti-Patterns' section that explicitly forbids the agent from asking users for secrets, API keys, p8 keys, or p12 certificates within the chat session, which is a strong preventative measure against accidental credential exposure.
- [REMOTE_CODE_EXECUTION]: While the skill mentions official packages such as 'react-native-onesignal' and 'onesignal_flutter' for instructional setup purposes, it does not contain any commands to install or execute remote code automatically.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied queries about SDK setup (ingestion points in SKILL.md). While it lacks explicit boundary markers or sanitization for this input, the skill has no dangerous capabilities such as file-system writes, network operations, or subprocess execution, minimizing the risk surface.
- [COMMAND_EXECUTION]: The skill is purely instructional and does not include any shell command execution or dynamic context injection patterns.
Audit Metadata