super-search

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's architecture is designed around data verification and quality control. It includes dedicated modules for authority scoring (analyze.ts) and adversarial review (review.ts) to ensure information reliability and mitigate the impact of unreliable or biased web content.
  • [COMMAND_EXECUTION]: The research pipeline is managed through the execution of internal Node.js scripts (search.ts, fetch.ts, etc.). These operations are contained within the skill's logic for processing data and do not involve executing untrusted user input as shell commands.
  • [REMOTE_CODE_EXECUTION]: No evidence of arbitrary remote code execution was detected. The skill uses standard Node.js APIs and relies on pre-installed environmental tools (such as search/fetch MCPs) rather than downloading and executing external binaries or scripts at runtime.
  • [DATA_EXFILTRATION]: The skill maintains a local cache in the user's home directory (~/.super-search-cache) to store public web content for performance. No sensitive local file access or unauthorized data transmission to external domains was observed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 07:15 AM
Security Audit — agent-trust-hub — super-search