The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a significant attack surface for indirect prompt injection due to its automated data ingestion process. Ingestion points: The skill is designed to crawl and process content from external, untrusted sources including websites, social media feeds, and press kits (documented in SKILL.md and references/asset-intake.md). Boundary markers: The instructions do not specify any delimiters or safety markers to prevent the agent from executing instructions that may be embedded in the retrieved assets. Capability inventory: The agent has capabilities to write to local configuration files (.agents/brand.md) and chain other generative skills based on its findings. Sanitization: The instructions lack requirements for sanitizing or filtering external content before it is interpolated into the agent's context or saved to files.
[EXTERNAL_DOWNLOADS]: The skill mandates automated network operations to gather brand information. The agent is instructed to fetch HTML/CSS, perform site screenshots, and download media assets from user-provided URLs and linked social media profiles (references/asset-intake.md).

brand