amann-evidence-standards
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional text and checklists for academic review standards within the Academy of Management Annals framework. It does not include executable scripts, shell commands, or network requests to external domains.
- [SAFE]: Mentions of external tools like StatsPAI and Stata MCP (‘bacon_decomposition’, ‘callaway_santanna’) refer to internal platform capabilities via a shared documentation resource. These represent standard tool usage for empirical audit and do not involve remote code execution from untrusted sources.
- [SAFE]: While the skill involves processing academic literature (external data), it is a set of guidelines for the AI's judgment rather than an automated script that handles untrusted input without oversight. No specific injection vulnerabilities were identified.
Audit Metadata