calendar-hardened

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill contains explicit guardrails to prevent the transmission of personally identifiable information, such as attendee emails and meeting notes, to unauthorized external endpoints.
  • [COMMAND_EXECUTION]: Requires 'curl' and 'jq' for interacting with calendar provider APIs. These operations are restricted by instructions requiring explicit user confirmation before creating, modifying, or deleting events.
  • [SAFE]: Analysis of the skill instructions and documentation shows a focus on data minimization and privacy, with no detected malicious patterns, obfuscation, or unauthorized access attempts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 06:30 PM
Security Audit — agent-trust-hub — calendar-hardened