node-inspect-debugger

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use shell commands such as node, npm, kill, and curl to start debug sessions, manage process signals, and query local inspector endpoints. These actions are standard for the described debugging tasks.- [EXTERNAL_DOWNLOADS]: The skill specifies downloading the chrome-remote-interface package from the official NPM registry to facilitate programmatic interaction with the Node.js debugger.- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests and processes data from running applications via the debugger (e.g., in SKILL.md via CDP evaluation). While it lacks explicit boundary markers or sanitization for this external data, this is inherent to the nature of a debugging tool and the risk is mitigated by the intended use-case.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 01:13 AM
Security Audit — agent-trust-hub — node-inspect-debugger