business-writer

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): The skill directly interpolates user text via the $ARGUMENTS variable without using delimiters such as triple quotes or XML tags. This allows untrusted input to potentially influence the agent's instructions.
  • Indirect Prompt Injection (LOW): The skill processes untrusted external content as its primary function. * Ingestion points: User-provided text in SKILL.md ($ARGUMENTS). * Boundary markers: Absent. * Capability inventory: None. The skill has no access to the file system, network, or shell, and only performs text-to-text transformations. * Sanitization: None detected.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 06:18 AM