node-inspect-debugger
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to use shell commands such as
node,kill,pgrep, andcurlto manage and inspect Node.js processes.\n- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install thechrome-remote-interfacepackage from the NPM registry to facilitate programmatic debugging.\n- [DYNAMIC_EXECUTION]: The skill provides a template for a JavaScript driver script (/tmp/cdp-debug.js) that is written and executed by the agent to automate interaction with the V8 inspector.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent ingests potentially untrusted data from a running process's memory (e.g., variables, call stacks). Malicious data in the debugged process could attempt to influence the agent's behavior.\n - Ingestion points: CDP
Runtime.getPropertiesandDebugger.evaluateOnCallFrameoutput (SKILL.md).\n - Boundary markers: Absent; data is processed as raw debug output.\n
- Capability inventory: Shell command execution and file system access (SKILL.md).\n
- Sanitization: Absent.
Audit Metadata