prompt-enhance

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a benign prompt engineering tool designed to improve the structure and token efficiency of markdown files. It does not perform unauthorized network operations, access sensitive credentials, or execute untrusted code.
  • [PROMPT_INJECTION]: The skill presents a potential surface for indirect prompt injection (Category 8) because it is designed to read and process the contents of external markdown files provided via the $ARGUMENTS variable. Ingestion points: File content loaded from the path specified in the target argument (SKILL.md). Boundary markers: The input file content is contained within XML-style tags. Capability inventory: The skill utilizes TaskCreate, AskUserQuestion, and standard file-system tools to read and refactor files. Sanitization: There is no explicit sanitization of the target file's content. This risk is inherent to any tool designed for document processing and optimization.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 07:25 AM