how-to-tutorial-writer

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection through its content research workflow.
  • Ingestion points: The workflow (SKILL.md, Step 2) instructs the agent to use web_search to gather step-by-step processes, product documentation, and competitor gaps from external websites.
  • Boundary markers: Absent. There are no instructions or delimiters provided to ensure the agent ignores instructions or adversarial patterns that might be present in the retrieved external data.
  • Capability inventory: The skill's capabilities are limited to generating markdown content, SEO metadata, and video outlines. It does not perform file system writes, command execution, or other high-risk operations.
  • Sanitization: Absent. The instructions do not describe any validation or escaping of external content before it is interpolated into the final output structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 07:32 AM