The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external websites using scraping tools like Firecrawl and Apify, which could potentially contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Website content is processed via the firecrawl_urls_scrape and web_pages_scrape tools as described in the 'Building the doc' section of SKILL.md.
Boundary markers: The instructions do not specify the use of technical delimiters or structured markers for separating scraped content from internal instructions.
Capability inventory: The skill has access to file system tools (create_file, edit_file) and downstream marketing skills that consume the generated context file.
Sanitization: The skill employs a strong human-in-the-loop mitigation by requiring the agent to present the draft to the user section-by-section for correction and verification before any data is saved to the persistent brand-context.md file.
[EXTERNAL_DOWNLOADS]: The skill references external tools and platforms to facilitate its branding and research capabilities.
Connects to the vendor's management interface at app.hyperfx.ai for tool configuration and MCP connectivity.
Utilizes third-party data extraction services including Firecrawl and Apify to automate the gathering of brand assets and customer language from public web pages.

brand-context