skills/sorawit-w/agent-skills/whoami/Gen Agent Trust Hub

whoami

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's behavior is entirely consistent with its stated purpose of creating and managing a user collaboration profile. It provides clear documentation on its operations and scope.
  • [DATA_EXFILTRATION]: The skill maintains a strong security posture regarding user data. It includes a specific data-handling policy that forbids the solicitation or storage of secrets (passwords, SSNs) and requires explicit confirmation before remembering any volunteered sensitive information.
  • [COMMAND_EXECUTION]: File system operations, such as creating the portable profile or updating the global Claude configuration, are performed transparently. The instructions emphasize that global persistence must be an opt-in feature requiring explicit user consent.
  • [PROMPT_INJECTION]: The instructions do not contain any patterns typical of prompt injection, such as attempts to bypass safety filters or override system-level constraints.
  • [EXTERNAL_DOWNLOADS]: No external downloads or remote code execution patterns were identified. The skill uses local assets and integrates with other user-installed skills via documented interfaces.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 07:12 AM
Security Audit — agent-trust-hub — whoami