The Agent Skills Directory

[COMMAND_EXECUTION]: The skill guides the user to perform shell operations using node and the mcpc CLI to interact with the Apify API.
[DATA_EXFILTRATION]: The run_actor.js script includes the APIFY_TOKEN as a query parameter in requests to api.apify.com. This is a standard integration method for this service, though it results in credentials appearing in the request URL.
[SAFE]: The script implements a security check in the csvCell function to prevent CSV Formula Injection (Excel Injection) by prefixing potentially dangerous leading characters with a single quote.
[PROMPT_INJECTION]: The skill processes untrusted data from social media and web platforms, which presents a surface for indirect prompt injection.
Ingestion points: External data is retrieved via Apify Actors in run_actor.js and displayed or saved to files.
Boundary markers: The skill lacks explicit delimiters or instructions to the agent to disregard instructions within the scraped content.
Capability inventory: The skill has the ability to write to the file system and perform network requests to the Apify API.
Sanitization: The script performs structural sanitization for CSV files but does not filter the content for adversarial natural language patterns.

apify-competitor-intelligence