skill-dependency-resolver

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOWNO_CODE
Full Analysis
  • [Metadata Analysis] (SAFE): The skill documentation and YAML schema indicate it is designed for structural analysis of other skills rather than executing untrusted code or accessing sensitive data stores.
  • [Indirect Prompt Injection] (LOW): The skill ingests untrusted data via the skills_directory and target_goal inputs. However, the described capabilities are limited to DAG construction and metadata mapping, which poses a low risk of code-based injection unless the implementation logic (which is not provided) handles these inputs unsafely.
  • [Implementation Visibility] (INFO): No source code (Python, JavaScript, etc.) was included in the analysis. The verdict is based on the provided SKILL.md and skill.yaml files which describe the intended behavior and interface.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 11:39 PM