writing-shape

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process 'raw material' from external markdown files provided by the user. This creates a surface for indirect prompt injection where malicious instructions hidden within the input text could attempt to subvert the agent's logic or the content of the output article.
  • Ingestion points: The agent reads an input 'pile' (markdown file) end-to-end (SKILL.md).
  • Boundary markers: The instructions do not specify any delimiters or safety warnings to treat the input pile as data rather than instructions.
  • Capability inventory: The agent has the capability to read files from disk and append/write to new article files on disk (SKILL.md).
  • Sanitization: No sanitization or filtering of the input content is mentioned before it is processed or used to 'ground' concepts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 06:39 PM