calendar

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHNO_CODEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill's primary function is to process untrusted external data (event titles and descriptions) while possessing write-level capabilities (event creation and meeting management).
  • Ingestion points: Data from Google, Apple, and Outlook calendar APIs.
  • Boundary markers: None specified in the documentation or instructions.
  • Capability inventory: Meeting scheduling, event creation, and sync operations using system binaries like curl.
  • Sanitization: No input validation or instruction-ignoring logic is present.
  • Command Execution (LOW): Metadata specifies requirements for curl and jq. While standard for API interaction, their usage with external data requires strict parameter sanitization to prevent command injection.
  • No Code (INFO): The provided skill contains only documentation and metadata; it lacks executable script files, making it an incomplete implementation or a documentation-only stub.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 07:51 AM