spec-interview
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed purely for documentation and requirement gathering through a guided interview process. It does not contain any scripts, remote downloads, obfuscation, or persistence mechanisms. The core functionality involves reading a local specification file and writing updates based on user interaction.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user input from an interview tool and interpolates it into a document template. This creates a standard surface for indirect prompt injection common in documentation assistants.
- Ingestion points: User responses to systematic interview questions across multiple domains defined in
SKILL.md. - Boundary markers: The skill uses a structured markdown template (
templates/spec-template.md) to delimit user-provided content. - Capability inventory: The agent is authorized to read and write local markdown files (e.g.,
SPEC.md). - Sanitization: No explicit escaping or validation of user-provided strings is defined in the instruction set.
Audit Metadata