aer-statspai
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for using a legitimate, author-affiliated Python library ('statspai') for econometric analysis. It includes built-in safeguards, such as the
bibtexcommand designed specifically to prevent the AI from inventing non-existent citations.- [EXTERNAL_DOWNLOADS]: The skill mentions standard installation viapip install statspai. The package is attributed to the skill's author ('brycewang-stanford') and represents normal vendor functionality for a scientific tool.- [COMMAND_EXECUTION]: The skill provides example code for data analysis (e.g.,sp.callaway_santanna). These are standard mathematical and statistical operations within a Python environment and do not involve unauthorized system access or dangerous subprocess calls.- [DATA_EXFILTRATION]: No network operations or sensitive file access patterns were found. The tool focuses on local data processing and local file export (e.g., exporting results to.latexor.docx).- [PROMPT_INJECTION]: The skill instructions do not contain any bypass attempts, role-play overrides, or instructions to ignore safety filters. It actually reinforces constraints by deferring methodological decisions to 'aer-identification'.
Audit Metadata