The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to bypass safety filters, override system instructions, or extract system prompts were detected. The skill uses structured roles to enhance design quality through criticism and constraints.
[DATA_EXFILTRATION]: No network operations, sensitive file path access, or credential exposure patterns were found. The skill operates within the conversational context.
[OBFUSCATION]: The content is provided in plain text. No Base64, hex encoding, zero-width characters, or homoglyph attacks were identified.
[REMOTE_CODE_EXECUTION]: There are no commands for downloading or executing external scripts, and no dependencies on third-party package registries.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not utilize the !command syntax or any other mechanism to execute shell commands at load time.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user-provided designs (untrusted data), it possesses no exploitable capabilities such as file-system writes, network access, or shell command execution, rendering the surface safe.

multi-agent-brainstorming