claim-matrix-rewriter

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely on local files within a user-specified workspace. It reads structured research data (JSONL) and bibliographic information (BIB) to generate a summary markdown file.
  • [SAFE]: No network activity is requested or performed by the script, and there are no signs of obfuscation or credential handling.
  • [SAFE]: The script uses standard Python libraries for file manipulation and regex, and relies on an internal 'tooling' module for atomic file writes and data parsing, which is typical for this class of research agent skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 01:59 PM