writing-beats

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing untrusted raw material and writing derived content to the file system. \n- Ingestion points: Markdown files containing raw material and the generated article file itself are read from disk during the process. \n- Boundary markers: No specific delimiters are used to isolate the raw material from the agent's internal instructions. \n- Capability inventory: The skill utilizes file read and write operations in SKILL.md. \n- Sanitization: Input data is not sanitized or validated for embedded instructions before being processed into article beats.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 03:45 PM
Security Audit — agent-trust-hub — writing-beats