The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions and scripts execute shell commands such as mcpc and node to manage actor metadata and run extraction tasks. These commands include environment variables loaded from a local .env file using the --env-file flag or shell redirection.
[EXTERNAL_DOWNLOADS]: The skill recommends installing the @apify/mcpc CLI tool from the npm registry to facilitate communication with Apify's Model Context Protocol (MCP) server.
[DATA_EXFILTRATION]: The skill reads the APIFY_TOKEN from the .env file and transmits it to Apify's official API endpoints (api.apify.com, mcp.apify.com). This is a standard and necessary operation for the skill's stated purpose of interacting with the Apify platform.
[PROMPT_INJECTION]: The skill fetches content from third-party websites (via Apify Actors) and asks the agent to summarize it, creating a surface for indirect prompt injection.
Ingestion points: Data is retrieved from the Apify API in reference/scripts/run_actor.js and displayed to the agent.
Boundary markers: The workflow does not define specific delimiters or instructions to separate untrusted external data from agent instructions.
Capability inventory: The skill has access to file system writes and network operations via the Node.js script.
Sanitization: Results are truncated for display but are not specifically sanitized to remove potentially malicious embedded instructions.

apify-trend-analysis