The Agent Skills Directory

[DATA_EXFILTRATION]: The skill accesses the .env sensitive file path to retrieve the APIFY_TOKEN. This occurs in SKILL.md via a grep command and in reference/scripts/run_actor.js by accessing process.env.APIFY_TOKEN. The token is used for authenticated requests to api.apify.com.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external web sources through various Apify Actors (e.g., social media posts, business reviews).
Ingestion points: reference/scripts/run_actor.js fetches and processes data from the Apify API (api.apify.com).
Boundary markers: None identified in the prompt templates or processing logic.
Capability inventory: The skill can perform network requests (fetch), write to the local file system (writeFileSync), and log data to the console.
Sanitization: The script includes a csvCell function to sanitize data against CSV formula injection (e.g., prefixing =, +, @, or - with a single quote) and truncates long text fields.
[COMMAND_EXECUTION]: The skill instructs the user to execute shell commands, including the mcpc CLI and a local Node.js script (reference/scripts/run_actor.js), which handles actor execution and data exporting.

apify-competitor-intelligence