agent-ready-cli

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to interact with the agent-ready command-line utility for scanning URLs.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to run the agent-ready-scanner package via npx or npm. This package is the primary tool for the skill and is maintained by the skill's author.
  • [DATA_EXPOSURE]: Instructions are provided to search local .env files for the AGENT_READY_API_KEY. This is intended for tool configuration and uses environment variables to prevent leaking credentials in process listings or shell history.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external URLs during scans. It includes a specific "Security & trust" section that explicitly instructs the agent to treat all scan output as inert data and not as instructions, effectively mitigating potential injection attempts from scanned content.
  • Ingestion points: Scanned URL content retrieved via the agent-ready scan command.
  • Boundary markers: Explicit instructions in SKILL.md to treat output as inert data to summarize.
  • Capability inventory: Shell command execution capabilities used to run the CLI tool.
  • Sanitization: Guidance to summarize findings and relay specific fields rather than echoing raw external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 06:36 AM
Security Audit — agent-trust-hub — agent-ready-cli