Introduction Writer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes user-provided topics and outlines without using boundary markers, which could allow embedded instructions to influence the model output. Evidence Chain: 1. Ingestion points: User-provided topic, summary, or outline in the workflow. 2. Boundary markers: None identified. 3. Capability inventory: No system-level capabilities (file access, network, or command execution) are present. 4. Sanitization: No input sanitization is performed.
- No Code (LOW): The skill consists entirely of markdown instructions and example data without any executable script files or dependencies.
Audit Metadata