improve-codebase-architecture

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI tool through the command gh issue create to automate the creation of refactoring RFCs. This command execution is a core feature of the skill but grants the agent write access to the external repository.
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) due to its data processing workflow. Ingestion points: The agent reads and processes arbitrary codebase files using the subagent_type=Explore capability (SKILL.md, Step 1). Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the exploration phase. Capability inventory: The skill possesses the capability to write persistent artifacts to an external system via gh issue create (SKILL.md, Step 7). Sanitization: The skill lacks explicit sanitization or validation of the codebase content before it is incorporated into the generated GitHub issues. The risk is elevated by the instruction to create issues without user review.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 12:27 PM