skills/hkuds/deeptutor/knowledge-base/Gen Agent Trust Hub

knowledge-base

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines several commands for interacting with the deeptutor utility via an exec tool. These commands are used for knowledge base lifecycle management and searching.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from knowledge base search results into the agent's context, which represents a potential indirect prompt injection surface.
  • Ingestion points: Output from deeptutor kb list and deeptutor kb search commands (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Use of the exec tool to run deeptutor CLI commands (SKILL.md).
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 08:25 AM
Security Audit — agent-trust-hub — knowledge-base