research-coach

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional text and evaluation criteria. No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected.
  • [NO_CODE]: No scripts, binaries, or executable files are included in the skill package. All operations are handled via natural language instructions.
  • [EXTERNAL_DOWNLOADS]: The skill and its rubric mention well-known, trusted government and educational domains (e.g., courts.gov, Mass.gov) as recommended research resources for users. These are documented for educational purposes and do not involve automated downloads or remote code execution by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 01:09 PM
Security Audit — agent-trust-hub — research-coach