android-research-library
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The instructions explicitly forbid including sensitive materials such as Expo tokens, Apple certificates, keystores, API keys, or
.envfiles in source code, documentation, or logs. It advocates for redacting values and using secure secret management paths. - [PROMPT_INJECTION]: No malicious patterns or bypass attempts were found. The skill includes defensive instructions, advising the agent to treat external inputs like web pages or app reviews as untrusted until corroborated.
- [COMMAND_EXECUTION]: The skill references standard development tools (e.g.,
npx expo install,npx expo prebuild) within its documentation for user guidance. It does not contain any automated or hidden execution patterns, such as dynamic context injection.
Audit Metadata