cron-writer

Warn

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches the 'ai-cron-gen' package from the official NPM registry at runtime using npx.
  • [REMOTE_CODE_EXECUTION]: The package content is executed immediately upon download. Without version pinning (e.g., ai-cron-gen@1.0.0), the skill executes the latest available code, which lacks integrity verification and could be modified by the package author without notice.
  • [COMMAND_EXECUTION]: The skill's core functionality is implemented through the execution of shell commands.
  • [PROMPT_INJECTION]: The skill interpolates natural language input directly into a shell command string, creating an indirect prompt injection surface.
  • Ingestion points: Schedule description strings (e.g., 'every day at midnight') provided as arguments to the npx command.
  • Boundary markers: None identified in the provided skill documentation to isolate user input from the shell syntax.
  • Capability inventory: Shell execution via npx.
  • Sanitization: No evidence of shell argument escaping or input validation is present in the skill instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 05:14 AM