coding-prefs

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFE
Full Analysis
  • [Persistent Memory Management]: The skill is designed to maintain a user-scoped file at /memory/coding-prefs.md. This allows the agent to persist coding styles, framework preferences, and other durable feedback provided by the user.
  • [Information Processing (Indirect Prompt Injection Consideration)]: As a memory-focused skill, it processes and stores user-supplied information to influence future behavior. Ingestion points: Data is read from /memory/coding-prefs.md. Boundary markers: The skill does not explicitly define delimiters for the content read from memory. Capability inventory: The skill is limited to reading and appending/replacing content within the specific /memory/coding-prefs.md file path; it lacks network access. Sanitization: No specific sanitization of the stored preferences is described.
  • [Minimal Attack Surface]: The skill does not include any executable code or external package requirements, significantly reducing the potential for common security risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 05:19 AM