paper-formatter
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill performs a runtime installation of the 'python-docx' library from the public PyPI registry using 'pip install' as seen in the workflow instructions in SKILL.md.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted manuscripts and sample papers provided by users, creating a potential surface for indirect prompt injection where instructions embedded in documents could attempt to influence the agent.
- Ingestion points: User-supplied manuscripts and journal sample papers (范文) in .docx, .tex, or plain text formats (specified in SKILL.md, Step 1).
- Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore instructions found within the processed files.
- Capability inventory: The skill possesses the ability to read and write files to the local system, execute Python scripts, and install third-party packages.
- Sanitization: The 'generate_latex.py' script includes an 'escape_latex' function to sanitize text for LaTeX output, and the 'python-docx' library handles standard XML entity escaping for Word documents.
Audit Metadata