get-context

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Modular Script Execution: The skill contains instructions to run a "preflight script" from a related local module (user-context/SKILL.md) when shell access is available. This is a standard initialization pattern for complex skill environments to ensure necessary prerequisites are met.
  • External Data Ingestion Surface: The instructions direct the agent to utilize external grounding materials, including saved product URLs, Figma files, screenshots, and codebase paths.
  • Ingestion points: Materials are sourced from user-provided URLs and local file system paths specified in SKILL.md.
  • Boundary markers: The skill establishes a "Hard boundary" preventing file creation or server execution until the design target is clarified, which serves as a functional gate.
  • Capability inventory: The skill mentions the ability to run scripts and potentially start servers or create files (noted in the restrictions section of SKILL.md).
  • Sanitization: Standard handling of design assets is expected; specific sanitization logic is managed by the agent's core processing of these file types.
  • Policy and Route References: The "Critical Overrides" section points the agent to centralized routing and safety documentation. This pattern is used to maintain consistency and follow established safety protocols across a modular skill set.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 09:18 AM
Security Audit — agent-trust-hub — get-context