peer-review-template

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions are benign and focused on a structured analytical workflow for peer reviews.
  • [NO_CODE]: The skill consists exclusively of Markdown documentation and prompt instructions. It does not include any scripts, binaries, or command-line executions.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to process external, untrusted content provided by the user for review.
  • Ingestion points: The skill explicitly requests "Work to review" and "Review template" from the user (SKILL.md).
  • Boundary markers: Absent. The skill does not define clear delimiters or "ignore instructions" wrappers for the ingested data.
  • Capability inventory: None. The skill does not invoke any tools, file system operations, or network requests, effectively neutralizing the risk of a successful injection leading to system compromise.
  • Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 03:18 AM