scientific-paper
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional Markdown content and LaTeX code templates. It does not include executable scripts, request system permissions through frontmatter configuration, or perform network operations. All external links reference trusted documentation for technical tools.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and edit existing LaTeX (.tex) and bibliography (.bib) files. 1. Ingestion points: User-provided research documents and reference files mentioned in the workflow sections of SKILL.md. 2. Boundary markers: Absent; the skill does not define specific delimiters to isolate user data from instructions. 3. Capability inventory: None; the skill does not define or request tool access. 4. Sanitization: Absent; the workflow relies on academic peer-review style checks rather than technical sanitization of document content.
Audit Metadata