explorbot-fundamentals

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill guides the agent to interact with the system via the explorbot CLI using npx. Provided commands include init, explore, context, shell, knows, and navigate. These are standard operational commands for the tool's stated purpose of web testing and environment initialization.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation hosted at https://raw.githubusercontent.com/testomatio/explorbot/main/docs/. This URL belongs to the official repository of the skill's author (Testomat.io), and the downloads consist of instructional JSON and markdown files.
  • [INDIRECT_PROMPT_INJECTION]: As an autonomous AI testing tool, Explorbot ingests data from external websites and local files to guide its behavior.
  • Ingestion points: Target URLs provided to the explore command and files within the knowledge/ and experience/ directories.
  • Boundary markers: The skill does not explicitly define markers or 'ignore' instructions for the data it processes.
  • Capability inventory: The tool drives a web browser, executes shell commands via npx, and writes reports and logs to the local filesystem.
  • Sanitization: The provided instructions do not detail specific sanitization or filtering of external content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 07:44 AM
Security Audit — agent-trust-hub — explorbot-fundamentals