atlas-inspired-writing

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional text for the AI agent to follow when assisting with academic writing, drafting, and revising manuscripts.
  • [SAFE]: No executable scripts, shell commands, or external dependencies are included in the skill package.
  • [SAFE]: The skill references an official ATLAS Style Guide PDF from CERN (cds.cern.ch), which is a well-known and trusted scientific institution.
  • [SAFE]: There are no indicators of prompt injection, data exfiltration, or obfuscation. The instructions prioritize user requests and venue-specific guidelines over the skill's defaults, which is standard behavior steering.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 10:06 AM