deep-interview
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a requirement-gathering interface that processes user-provided ideas and interview responses into a technical specification. This specification is subsequently used as input for execution agents.
- Ingestion points: Initial ideas provided in
{{ARGUMENTS}}and user answers during the interview loop inSKILL.md. - Boundary markers: No explicit delimiters are used to separate user-provided content from the system instructions in the generated specification.
- Capability inventory: The skill utilizes the
exploreagent for codebase analysis, writes state and specification files to the.omc/directory, and invokes other specialized skills for planning and execution. - Sanitization: The process relies on the underlying LLM's safety guardrails and requires explicit user approval before triggering any execution-oriented skills.
- [EXTERNAL_DOWNLOADS]: The skill's documentation contains an informational link to an external GitHub repository (
github.com/Q00/ouroboros) to provide methodological context. No automated download or execution of remote code is performed.
Audit Metadata