writing-beats

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it processes user-provided markdown files as 'raw material'. 1. Ingestion points: raw material markdown file. 2. Boundary markers: absent. 3. Capability inventory: file read and write access. 4. Sanitization: absent. However, the risk is mitigated by the interactive 'choose-your-own-adventure' workflow which requires explicit user review and selection before any content is written to disk.
  • [COMMAND_EXECUTION]: The skill performs standard file system operations including reading from source material and appending beats to an article file. These actions are performed at paths agreed upon with the user and are central to the skill's purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 03:09 AM
Security Audit — agent-trust-hub — writing-beats