improve-codebase-architecture

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository and uses it to generate architectural recommendations and GitHub issues.
  • Ingestion points: The skill reads CONTEXT.md, domain glossary files, and Architectural Decision Records (ADRs) found within the project repository to inform its analysis.
  • Boundary markers: There are no identified boundary markers or instructions to the agent to disregard potential instructions embedded within the ingested files.
  • Capability inventory: The skill is capable of spawning parallel sub-agents for design exploration and creating external GitHub issues using a provided template.
  • Sanitization: The skill lacks explicit sanitization or validation logic for the content ingested from the project files before it is processed or used to generate issues.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 09:06 AM
Security Audit — agent-trust-hub — improve-codebase-architecture