paper-self-review
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely through natural language instructions guiding the agent to review and analyze user-provided text. It does not include executable scripts, shell commands, or configuration for external tools.
- [SAFE]: External references point to established educational resources and public GitHub repositories relevant to academic writing (e.g., simon.peytonjones.org and github.com/hzwer/WritingAIPaper). These are documented for context and do not involve remote code execution or automated downloads.
- [SAFE]: While the skill is designed to ingest and process untrusted user data (research paper drafts), it does not possess exploitable capabilities such as file system write access, network operations, or dynamic code execution that could be used for an attack.
Audit Metadata