skills/daxaur/openpaw/c-calendar/Gen Agent Trust Hub

c-calendar

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on executing external binaries including gog, icalBuddy, and osascript to perform calendar operations.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and processes event details (titles, descriptions, attendee lists) from external calendar services which may contain adversarial instructions.
  • Ingestion points: Output from gog cal list, gog cal get, and various icalBuddy commands.
  • Boundary markers: None identified; the agent processes raw command output containing potentially untrusted strings.
  • Capability inventory: Includes the ability to create, update, and delete events via gog and execute scripts via osascript.
  • Sanitization: No sanitization or validation steps are defined for the event content before it is parsed by the agent.
  • [DATA_EXFILTRATION]: Accesses sensitive private information from local Apple Calendar databases and remote Google Calendar accounts, exposing schedule and contact data to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:44 AM
Security Audit — agent-trust-hub — c-calendar