The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override agent behavior or bypass safety guidelines were found. The example prompts provided are standard use-case queries related to Keychain implementation.\n- [DATA_EXFILTRATION]: No network operations or access to sensitive local system files were detected. The skill focuses on legitimate local storage using official system APIs.\n- [EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads or reference untrusted remote scripts. All references are to internal documentation or well-known developer forums.\n- [COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or scripts that execute arbitrary commands. The included Swift code snippets are for educational purposes within the context of application development.\n- [CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or private tokens are present. The skill correctly uses placeholders and instructs the user on secure credential management practices.

axiom-keychain