The Agent Skills Directory

[PROMPT_INJECTION] (SAFE): No instructions found that attempt to override agent behavior, bypass safety guidelines, or extract system prompts. The content is strictly limited to React programming advice.
[DATA_EXFILTRATION] (SAFE): No sensitive file paths, hardcoded credentials, or network operations targeting non-whitelisted domains were detected. The fetch example provided is a standard educational code snippet and not an instruction for the agent to execute unauthorized network calls.
[REMOTE_CODE_EXECUTION] (SAFE): The skill does not contain any commands for downloading scripts or executing remote code. It lacks any package installation commands or dynamic execution patterns.
[NO_CODE] (SAFE): This skill is entirely documentation-based. It provides guidance and code examples within a Markdown file but does not include any executable scripts, binaries, or configuration files that could pose a runtime risk.
[INDIRECT_PROMPT_INJECTION] (LOW): While the skill is designed to process user-provided React code (untrusted data), it lacks dangerous capabilities such as file-writing, subprocess execution, or network access, making it a safe advisory tool.

react-useeffect-audit