The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions attempting to override agent behavior or bypass safety constraints were detected in the skill markdown or metadata.
[Data Exposure & Exfiltration] (SAFE): The skill correctly implements expo-secure-store for token management. There are no patterns involving the exfiltration of sensitive local data or hardcoded credentials beyond standard placeholders.
[Obfuscation] (SAFE): No encoded strings, homoglyphs, or zero-width characters were found.
[Unverifiable Dependencies] (SAFE): All referenced libraries (expo-auth-session, expo-secure-store, google-auth) are standard, reputable packages for the specified platform.
[Command Execution] (SAFE): No shell commands, subprocess spawning, or unsafe script executions are present.
[Indirect Prompt Injection] (SAFE): The skill serves as a static reference for developers; it does not ingest or process untrusted external data that could influence the agent's behavior.
[Dynamic Execution] (SAFE): No use of eval(), exec(), or unsafe deserialization like pickle was found in the provided snippets.

rn-auth