skills/andiedie/cd2-skills/cd2/Gen Agent Trust Hub

cd2

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using npx @andie/cd2 to perform file management tasks such as listing, moving, and deleting files.
  • [EXTERNAL_DOWNLOADS]: Fetches and executes the @andie/cd2 package from the NPM registry. This package is part of the author's namespace and provides the core CLI functionality for the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through data processed from external sources.
  • Ingestion points: Processes the stdout results (JSON) from the CloudDrive2 CLI, which includes metadata from external file storage.
  • Boundary markers: No boundary markers or instructions to ignore embedded commands are present in the processing logic.
  • Capability inventory: Supports file reads, file writes, and command execution via the CLI tool.
  • Sanitization: No sanitization or validation of the CLI output is described before it is consumed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:03 AM
Security Audit — agent-trust-hub — cd2