The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override system behavior, bypass safety guidelines, or extract system prompts were detected. The instructions are focused entirely on frontend engineering workflows.
[DATA_EXFILTRATION]: The skill does not perform unauthorized network requests or access sensitive local files such as credentials, SSH keys, or environment variables.
[REMOTE_CODE_EXECUTION]: No remote script downloads or dynamic code execution patterns (like eval or exec) were found.
[COMMAND_EXECUTION]: There are no instances of dangerous shell command execution. The skill utilizes standard platform-provided tools for documentation lookup which are part of the intended workflow.
[OBFUSCATION]: The content is clear and readable. No Base64, zero-width characters, or hidden payloads were identified.
[INDIRECT_PROMPT_INJECTION]: The skill inherently processes existing codebase structures and conventions in Phase 1 (Context Discovery). This represents a standard input surface for AI agents in development tasks. The skill does not explicitly provide sanitization logic, but its structured approach and strict quality gates (TypeScript strict mode, mandatory test coverage) provide inherent defensive layers against accidental obedience to instructions embedded in analyzed source code.

senior-frontend