content-research-writer

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill instructions or workflows. The skill primarily focuses on text generation and organizational tasks within a local writing directory as defined in the Setup Your Writing Environment section of SKILL.md.\n- [PROMPT_INJECTION]: While the skill's research function involves ingesting external data, which is an inherent surface for indirect prompt injection, this is expected behavior for a research tool and does not present an elevated risk given the scope.\n
  • Ingestion points: External research data retrieved via web searches during the 'Conduct Research' phase.\n
  • Boundary markers: None explicitly defined in the provided markdown file.\n
  • Capability inventory: The skill is focused on generating outlines, providing feedback, and managing files in a user-created 'writing' directory.\n
  • Sanitization: The skill relies on standard agent-side processing of retrieved text.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 07:38 PM