paper-review
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional Markdown and YAML configuration. No executable scripts, binaries, or shell commands are included within the skill package.
- [SAFE]: The skill does not perform any network operations, external downloads, or file system modifications beyond non-mutating manuscript analysis.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of academic manuscripts. This ingestion surface is secured by explicit instructions to the agent to distinguish between direct results and speculation, verify evidence status (S0-S4), and adhere to a strict 'Manuscript-Integrity Base'. These logical boundaries prevent the agent from being manipulated by potentially malicious instructions embedded in a manuscript.
- [SAFE]: The references to external 'Wenyu-Type' projects and 'Ethan-style' overlays are consistent with the skill's stated purpose and the author's identity (wenyuchiou). These modules provide stylistic and domain-specific context without introducing security risks.
Audit Metadata