yao-chatgpt-crawler

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The Node.js scripts chatgpt_batch_crawl.mjs, chatgpt_browser_crawl.mjs, and preflight.mjs utilize the child_process module to orchestrate the crawling workflow. Specifically, they use spawn, execFileSync, and execFile to invoke the opencli tool and other local scripts. These commands use array-based argument passing rather than shell strings, which effectively prevents command injection vulnerabilities.
  • [SAFE]: The skill's behavior is consistent with its stated purpose of collecting and analyzing AI search results. It maintains all collected evidence (answers and logs) in a local directory and does not transmit data to unauthorized third-party servers. The use of an optional OPENAI_API_KEY via environment variables for semantic review is a standard and secure implementation for AI-enhanced analysis. No evidence of obfuscation, persistence, or privilege escalation was found across the 23 files provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 04:12 AM
Security Audit — agent-trust-hub — yao-chatgpt-crawler