skills/vm0-ai/vm0-skills/deep-dive/Gen Agent Trust Hub

deep-dive

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill reads local codebase files to analyze architecture, dependencies, and data flow. All findings are written to a local 'deep-dive/' directory for documentation purposes.
  • [INDIRECT_PROMPT_INJECTION]: The 'deep research' operation ingests data from the codebase, which could contain malicious instructions. However, the risk is mitigated by the skill's specific focus on fact-gathering and documentation, with explicit restrictions against suggesting implementation steps or taking autonomous actions based on the research.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 04:43 PM