gws-calendar-insert

Pass

Audited by Gen Agent Trust Hub on Oct 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data which could contain malicious instructions.
  • Ingestion points: The --summary, --location, --description, and --attendee flags in SKILL.md accept free-text input.
  • Boundary markers: Absent. No delimiters or 'ignore' instructions are provided for the input fields.
  • Capability inventory: The skill performs command execution using the gws tool to create calendar events.
  • Sanitization: Absent. There is no evidence of input escaping or validation before interpolation into the shell command.
  • [COMMAND_EXECUTION]: The skill utilizes the gws command-line utility. While this is the intended primary functionality, it involves executing a binary on the host system with arguments derived from user input.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 18, 2026, 12:31 PM