The Agent Skills Directory

[DATA_EXPOSURE]: No hardcoded credentials or sensitive file exfiltration patterns were found. The skill explicitly promotes secure environment variable handling by isolating .env ownership to applications rather than shared packages.
[REMOTE_CODE_EXECUTION]: No suspicious remote code downloads or execution patterns were identified. The suggested commands are standard development tools like turbo, bun, vitest, and oxlint.
[PROMPT_INJECTION]: No attempts to override system prompts or bypass safety guardrails were detected. The instructions maintain a clear focus on technical architecture.
[COMMAND_EXECUTION]: The skill defines a set of standard development scripts and Turborepo tasks. These are consistent with the skill's stated purpose of monorepo orchestration and do not include malicious command injection or privilege escalation attempts.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes repository structures and workspace manifests. While this involves processing external data, the skill does not possess dangerous capabilities that could be subverted through these ingestion points.

turborepo-architecture