tml-interview
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown documentation and system prompt instructions. No executable scripts, binaries, or active code components are present in any of the analyzed files.
- [NO_CODE]: No code was detected in the skill. The functionality is delivered purely through natural language instructions for the AI agent.
- [SAFE]: A reference to an external JSON schema ('https://themissinglayer.dev/schema/v1') is present in 'chatgpt-system-prompt.md'. This is a static data-structure reference and does not involve remote code execution.
- [SAFE]: The skill identifies an attack surface for indirect prompt injection by processing user-provided documents (e.g., SOPs) in 'chatgpt-system-prompt.md'. Ingestion points: User-pasted content. Boundary markers: Absent. Capability inventory: Limited to text generation only. Sanitization: Absent. The risk is assessed as minimal because the skill lacks high-privilege capabilities such as file system access or network write operations.
Audit Metadata