The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs users to download and execute the @coldiq/mcp package from the public NPM registry. This package is a core component of the author's data enrichment platform.
[COMMAND_EXECUTION]: Provides a specific shell command (npx -y @coldiq/mcp@latest) to be executed by the user to initialize the author's Model Context Protocol (MCP) server.
[PROMPT_INJECTION]: The skill incorporates external data from third-party websites and social media engagement into its drafting process, creating an attack surface for indirect prompt injection.
Ingestion points: SKILL.md identifies mcp__coldiq__fetch_page_content and mcp__coldiq__extract_post_engagement as sources of external text.
Boundary markers: No explicit delimiters or instructions are provided to help the model distinguish between safe data and potentially malicious instructions within the fetched content.
Capability inventory: The skill is used to generate personalized cold email drafts.
Sanitization: There is no mention of sanitization or validation of the content retrieved from external URLs before it is processed by the model.

first-touch