interview-script
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user research context and external files, which creates an ingestion surface.
- Ingestion points: Research objectives provided via $ARGUMENTS and external documents such as personas, hypothesis lists, and briefs referenced in SKILL.md.
- Boundary markers: Absent; the skill does not use delimiters or specific warnings to isolate external data.
- Capability inventory: Benign; the skill is limited to generating text and does not request network access, file system modifications, or shell execution.
- Sanitization: Absent.
Audit Metadata