debug-mode

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands to manage a local log collector server. In SKILL.md, it uses curl to check the health of a local service and bun to start a collector script (bun ./scripts/start-collector.mjs). It also uses bun to clear logs (bun ./scripts/clear-logs.mjs). These operations are restricted to the local environment (127.0.0.1) and are part of the skill's core functionality for runtime debugging.
  • [EXTERNAL_DOWNLOADS]: The skill uses curl and fetch to interact with a local server hosted at http://127.0.0.1:7777. These are local network requests used for service health checks and data ingestion. No external or untrusted remote sources were identified.
  • [DATA_EXFILTRATION]: The skill collects runtime data (variable values, execution paths) and sends it to a local ingestion endpoint (http://127.0.0.1:7777/ingest). The instructions explicitly warn against logging sensitive data such as passwords, tokens, or PII. The data remains within the local development environment.
  • [DYNAMIC_EXECUTION]: The skill utilizes spawn with detached: true in scripts/start-collector.mjs to run the collector server as a background process. This is a standard method for managing long-running utility services in developer tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 09:11 PM
Security Audit — agent-trust-hub — debug-mode