The Agent Skills Directory

[NO_CODE]: This skill is entirely instructional and does not contain any executable scripts, binaries, or shell commands. It operates solely through the agent's natural language processing.
[SAFE]: No malicious patterns, such as hardcoded credentials, obfuscated code, or unauthorized network requests, were detected. The persona instructions are standard and do not attempt to bypass security filters.
[PROMPT_INJECTION]: The skill acts as an analysis tool for external code and data flows, which is an indirect prompt injection surface. However, since the skill has no built-in capabilities to execute code or access the network, the risk is negligible.

fullstack-developer