paper-introduction-argument-writer

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions and referenced documents provide legitimate writing assistance for academic papers. Operations are limited to reading project-related documentation and writing markdown plans or LaTeX drafts within the current project scope.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it reads and processes external, potentially untrusted content from the user's project directory (e.g., LaTeX draft files and existing project metadata).
  • Ingestion points: LaTeX files (main.tex, paper.tex, sections/*.tex) and local agent metadata in the paper/.agent/ directory.
  • Boundary markers: No specific delimiters or safety instructions are used to separate external text from agent instructions.
  • Capability inventory: The skill has access to Read, Write, Edit, Bash, WebSearch, and WebFetch tools.
  • Sanitization: No input validation or content filtering is performed on the ingested paper content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 09:32 AM
Security Audit — agent-trust-hub — paper-introduction-argument-writer