research-methodology

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is comprised solely of markdown-based instructions, methodologies, and templates. It does not contain any executable scripts (Python, JavaScript, Shell) or binary files.
  • [NO_CODE]: No code was found within the skill directory. All files are markdown (.md) documents containing methodology guidance or structured templates.
  • [SAFE]: No credential harvesting, data exfiltration, or persistence mechanisms were detected. The skill focuses on guiding the AI to use legitimate, platform-provided tools for research tasks.
  • [SAFE]: The methodology emphasizes safety and accuracy by instructing the agent to perform source evaluation (CRAAP test), triangulation, and technical verification of external claims.
  • [SAFE]: All external references, such as SEC EDGAR or GitHub, are well-known, public services used for their intended research purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 05:21 PM
Security Audit — agent-trust-hub — research-methodology