preview-interview
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions.
- Ingestion points: The workflow identifies the use of resumes, job descriptions, and company context as primary inputs for generating interview materials (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' markers when interpolating user-provided documents into the prompt context.
- Capability inventory: The skill definition and reference files do not include any tools or instructions for network operations, file writing, or command execution; its actions are limited to text generation and critique within the agent's context.
- Sanitization: There is no evidence of input validation, filtering, or escaping for the processed documents.
Audit Metadata