interview-script
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions. The content is limited to natural language guidance for qualitative research.
- [PROMPT_INJECTION]: The skill is designed to ingest external context such as personas and research goals, which creates an indirect prompt injection surface. This risk is assessed as safe because the skill does not possess any dangerous capabilities such as network access, file system writing, or command execution. Ingestion points: File input for personas and research goals in SKILL.md. Boundary markers: None. Capability inventory: None. Sanitization: None.
Audit Metadata