skills/mrclrchtr/supi/codebase-design/Gen Agent Trust Hub

codebase-design

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill files consist entirely of documentation (Markdown) and configuration (YAML) files describing architectural principles.
  • [NO_CODE]: No executable code, shell scripts, or binary files are present in the skill.
  • [PROMPT_INJECTION]: The instructions do not contain patterns intended to bypass safety filters or override agent constraints.
  • [DATA_EXFILTRATION]: There are no network calls, hardcoded credentials, or instructions to access sensitive local files.
  • [REMOTE_CODE_EXECUTION]: No package managers are invoked and no remote scripts are downloaded or executed.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a process for analyzing user-provided codebase structures. While this involves processing untrusted data, the skill's purpose is to provide text-based architectural feedback, which does not grant dangerous capabilities or expose sensitive interfaces.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:20 AM
Security Audit — agent-trust-hub — codebase-design