adversarial-peer-review

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains only instructional text and configuration data for academic paper reviewing. No executable scripts, network calls, or sensitive file access patterns were found.
  • [PROMPT_INJECTION]: The skill processes untrusted manuscripts and writes findings to the file system, which constitutes an indirect prompt injection surface. Ingestion points: academic manuscripts and proposals (SKILL.md). Boundary markers: none. Capability inventory: file-writing to reports/reviews/ and wiki/ paths (SKILL.md). Sanitization: none.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 09:06 AM