Skills
skills/andrejones92/canifi-life-os/google-calendar/Gen Agent Trust Hub

google-calendar

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • REMOTE_CODE_EXECUTION (CRITICAL): The skill promotes the execution of remote scripts from an untrusted source via piped shell commands, which can lead to complete system compromise.
  • Evidence: curl -sSL https://canifi.com/skills/google-calendar/install.sh | bash found in SKILL.md.
  • Evidence: curl -sSL https://canifi.com/install.sh | bash found in SKILL.md.
  • CREDENTIALS_UNSAFE (HIGH): The skill documentation explicitly instructs users to store sensitive passwords in environment variables, which can be exposed through logs or process inspection.
  • Evidence: The 'Option 2: Environment Variables' section in SKILL.md suggests using canifi-env set SERVICE_PASSWORD "your-password".
  • PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection as it processes untrusted calendar data that could contain malicious instructions for the agent.
  • Ingestion points: Calendar event titles, descriptions, and attendee lists via Playwright automation in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Shell script execution and browser automation capabilities.
  • Sanitization: Absent.
Recommendations
  • HIGH: Downloads and executes remote code from: https://canifi.com/skills/google-calendar/install.sh, https://canifi.com/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 17, 2026, 05:23 PM
Security Audit — agent-trust-hub — google-calendar