writing-beats

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's logic is focused on content creation and file management for writing. No malicious code patterns or suspicious behaviors were identified.
  • [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection because it processes raw material and user-edited articles without explicit delimiters.
  • Ingestion points: The skill reads from a user-provided raw material markdown file and the target article file on disk.
  • Boundary markers: There are no specific instructions to use XML tags or delimiters to isolate the content of the raw material from the agent's instructions.
  • Capability inventory: The skill performs file reading and writing. It does not utilize network-enabled tools or shell execution capabilities.
  • Sanitization: The instructions do not define methods for sanitizing or escaping the content read from external files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 01:52 AM
Security Audit — agent-trust-hub — writing-beats