research-planning
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- General Analysis (SAFE): The skill is composed entirely of Markdown documentation and reference templates. No executable scripts (.py, .js, .sh, etc.) are included in the package.
- Data Exposure & Exfiltration (SAFE): Analysis of the references and workflow shows no attempts to access sensitive file paths (e.g., credentials, SSH keys) or establish outbound network connections.
- Prompt Injection (SAFE): The provided prompt templates (Paper2Code, AI-Researcher, AgentLaboratory) use standard instructional personas. There are no instructions to bypass safety filters, override system constraints, or extract system prompts.
- Dependency Analysis (SAFE): While the templates suggest formats for listing required Python packages (e.g., torch, numpy), the skill does not perform any automated installations or remote script executions.
Audit Metadata