writing-beats

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, unauthorized command execution, or data exfiltration attempts were detected. The skill instructions are focused on providing a narrative construction workflow.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes external raw materials and reads back generated files from disk. 1. Ingestion points: Input raw material (Markdown) and the generated article file. 2. Boundary markers: None present. 3. Capability inventory: Local file read and write operations. 4. Sanitization: No sanitization of input content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 10:16 AM
Security Audit — agent-trust-hub — writing-beats