ml-paper-writing
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes a
Makefilein the NeurIPS template directory that can fetch updated style files from the official NeurIPS media server (media.neurips.cc). This is a documented administrative feature using a well-known academic domain. - [COMMAND_EXECUTION]: The instructions provide common shell commands for the agent to explore research repositories (using
findandgrep) and compile documents (usingpdflatexorlatexmk). These operations are essential for the skill's primary function of paper writing and do not involve privilege escalation or sensitive file access. - [SAFE]: The skill implements strict citation verification workflows to ensure academic integrity and prevent AI hallucinations. It relies on standard, well-known academic APIs such as Semantic Scholar and CrossRef. Analysis of the 58 files found no evidence of prompt injection, data exfiltration, or obfuscated malicious logic.
Audit Metadata