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 in SKILL.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 explore agent 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
Risk Level
SAFE
Analyzed
Oct 31, 2026, 12:29 PM