The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override system safety guidelines or bypass instructions were detected. The skill uses standard role-play framing to establish a professional artistic persona.
[DATA_EXFILTRATION]: No network operations, sensitive file access, or credential harvesting patterns were found. The skill does not interact with external APIs or local sensitive data stores.
[REMOTE_CODE_EXECUTION]: No remote script execution or unverifiable dependency downloads are present. Installation instructions provided for various platforms are standard configuration steps and do not involve executing untrusted remote code.
[OBFUSCATION]: The content is entirely in clear text markdown. No Base64, zero-width characters, or hidden payloads were identified.
[COMMAND_EXECUTION]: The skill does not use system commands, subprocess spawning, or dynamic code execution. All logic is contained within the natural language instructions.
[CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or passwords were found in the skill or its reference files.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user input (briefs), it lacks dangerous capabilities like network access or file system writes that could be exploited via malicious input. It includes diagnostic frameworks to evaluate user requests safely.

illustrator