write-paper

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands via 'make' (specifically 'make paper' and 'make check') to automate the compilation of LaTeX manuscripts and perform format validation.
  • [EXTERNAL_DOWNLOADS]: The procedure involves fetching official LaTeX templates from academic venue websites to ensure correct formatting. These downloads are directed by the user based on the selected venue.
  • [DATA_EXFILTRATION]: (Indirect Prompt Injection Surface) The skill ingests untrusted external data from 'survey/survey.pdf' and various contribution reports. This data is distilled into the manuscript. While this presents an indirect prompt injection surface, it is consistent with the skill's primary purpose of synthesizing research materials into a paper.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 02:02 PM
Security Audit — agent-trust-hub — write-paper