writing-shape

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external markdown files as its primary source of material, creating a surface for indirect prompt injection.
  • Ingestion points: The agent reads a user-provided markdown file referred to as the "raw material" or "pile" (SKILL.md).
  • Boundary markers: There are no instructions to use delimiters or "ignore embedded instructions" warnings when processing the input pile.
  • Capability inventory: The agent has the capability to read files from disk and append content to a new or existing article file on disk (SKILL.md).
  • Sanitization: The instructions do not include steps to sanitize, escape, or filter instructions that might be embedded within the raw material before they are used to shape the article or influence the agent's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 04:20 AM