The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions for downloading and running the author's official MCP server package from the NPM registry via npx -y @coldiq/mcp@latest.
[COMMAND_EXECUTION]: Includes instructions for the user to configure environment variables and execute shell commands to initialize the author's enrichment tools.
[DATA_EXFILTRATION]: The skill communicates with the author's official API at api.coldiq.com to retrieve professional enrichment data and verify contact details, which is consistent with its stated purpose.
[PROMPT_INJECTION]: The skill processes external data including social media posts, profile bios, and company news, which presents a surface for indirect prompt injection.
Ingestion points: Data enters the context through tool calls such as mcp__coldiq__extract_post_engagement, mcp__coldiq__enrich_person, and mcp__coldiq__fetch_page_content.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when processing the retrieved external content.
Capability inventory: The skill utilizes tools with the ability to find and verify email addresses based on research results.
Sanitization: There are no explicit instructions or mechanisms defined for the validation or sanitization of content retrieved from external sources before it is processed by the agent.

personalization-6-buckets