content-research-writer

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill is composed of purely instructional markdown for guiding an AI agent through a writing and research workflow. It suggests standard terminal commands (mkdir, touch) for the user to organize files locally, which do not pose a security risk. While the skill possesses an attack surface for indirect prompt injection by ingesting external research data, this is inherent to its intended function as a research tool and no malicious instructions are present.
  • Ingestion points: External research sources and user-provided writing samples.
  • Boundary markers: None specified in the instructions.
  • Capability inventory: Local file system organization and web search functions.
  • Sanitization: Standard model guardrails apply; no explicit sanitization is defined in the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 12:36 AM