style-extract

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user-provided articles to extract style dimensions used in file-writing operations.
  • Ingestion points: User-provided articles and text snippets analyzed during the style extraction process (Mode A).
  • Boundary markers: None identified; the instructions do not specify any delimiters or safety prompts to isolate the processed text from the agent's logic.
  • Capability inventory: The skill performs file system operations including directory creation and writing/updating multiple JSON files within the ./writing-workspace/styles/ directory.
  • Sanitization: None; analyzed content is mapped directly to JSON fields without validation or escaping, allowing potentially malicious instructions in the article to influence the style profile output.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 06:58 AM