calendar

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes potentially untrusted external data within calendar event fields, creating a surface for indirect prompt injection attacks.
  • Ingestion points: Event fields such as title, description, and location in file SKILL.md.
  • Boundary markers: None identified; no delimiters or instructions to ignore embedded commands are present in the tool definitions.
  • Capability inventory: No file system access, network requests, or shell execution capabilities are defined in the skill.
  • Sanitization: No validation or escaping of event content is specified before processing or display.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 06:58 PM