The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Node.js script (run_actor.js) and the mcpc CLI tool to perform discovery tasks. These commands are integral to the skill's functionality and are restricted to interacting with the Apify platform.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of @apify/mcpc, an official tool from a well-known service provider (Apify). The download and use of this tool are documented neutrally as they represent standard integration with the platform.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external social media profiles, posts, and comments via Apify Actors. This content is attacker-controllable and may contain instructions intended to influence the agent's behavior.
Ingestion points: Social media metrics and text content retrieved via the run_actor.js script from api.apify.com.
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious embedded content in the results.
Capability inventory: The skill includes local file system write capabilities (writeFileSync) and network access to the Apify API.
Sanitization: The run_actor.js script performs basic CSV formula injection prevention and truncates long text fields, providing some defense against large-scale injection attempts.

apify-influencer-discovery