engineering-best-practices-enforcer

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled shell script scripts/scan-quality-signals.sh that utilizes ripgrep (rg) to scan for code quality signals such as @ts-ignore, ESLint markers, and potential React anti-patterns. It additionally prescribes the use of pnpm for verification steps (lint, typecheck, test, build).
  • [EXTERNAL_DOWNLOADS]: The skill includes an index of official documentation URLs for widely used libraries and frameworks including React (react.dev), TanStack (tanstack.com), TypeScript (typescriptlang.org), date-fns (date-fns.org), and Zod (zod.dev). These references are for documentation purposes and originate from well-known, trusted domains.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to its core function of processing repository content.
  • Ingestion points: The skill ingests untrusted data from the local repository files during code scans and reviews.
  • Boundary markers: No specific delimiters or instructions to ignore embedded instructions within processed files are explicitly defined.
  • Capability inventory: The skill has access to execute local scripts and standard development CLI tools (pnpm).
  • Sanitization: The skill does not explicitly sanitize the content of the files it reads before presenting them to the agent for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:20 PM