The Agent Skills Directory

[Prompt Injection] (SAFE): The instructions are limited to providing branding standards (colors, fonts). There are no attempts to override agent behavior, extract system prompts, or bypass constraints.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network exfiltration patterns were detected. The use of hex codes and RGB values for styling is benign.
[Unverifiable Dependencies] (SAFE): The skill references the standard 'python-pptx' library for color application, which is a reputable package for generating PowerPoint files. No suspicious remote scripts or piped installations are present.
[Indirect Prompt Injection] (SAFE): While the skill is designed to process external content ('any sort of artifact'), it lacks the high-risk capabilities (like subprocess execution or raw evaluation) that typically make this an exploitable surface. Its function is limited to formatting.
[Obfuscation] (SAFE): The content is clear and uses standard Markdown formatting with no encoded strings, zero-width characters, or homoglyphs.

brand-guidelines