codebase-simplify

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is strictly limited to read-only codebase analysis. It focuses on identifying architectural patterns such as unused surfaces, duplicate logic, and speculative generality.
  • [COMMAND_EXECUTION]: The instructions specify the use of rg (ripgrep) for searching symbols and strings within the local codebase. This is a standard utility for code navigation and auditing and is used in a non-destructive, read-only manner.
  • [DATA_EXFILTRATION]: There are no network operations, API calls, or instructions to transmit repository data to external domains. The skill explicitly states that the external state must remain unchanged.
  • [PROMPT_INJECTION]: The skill does not contain any patterns typical of prompt injection, such as attempts to bypass safety filters, role-play as a jailbroken AI, or ignore system instructions.
  • [REMOTE_CODE_EXECUTION]: The skill does not download or execute any external scripts or packages. It relies on internal logic and standard searching tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:59 PM
Security Audit — agent-trust-hub — codebase-simplify