The Agent Skills Directory

[SAFE]: No malicious patterns or behaviors detected. The skill performs its stated purpose of scraping leads through the Apify platform.
[CREDENTIALS_UNSAFE]: Follows security best practices by instructing the user to manage the Apify API token via a .env file instead of hardcoding credentials.
[EXTERNAL_DOWNLOADS]: References the official @apify/mcpc tool from the npm registry, which is an expected dependency for Apify integrations.
[PROMPT_INJECTION]: The skill processes external data scraped from the web via Apify Actors, creating a surface for indirect prompt injection.
Ingestion points: Actor results are downloaded from Apify datasets in reference/scripts/run_actor.js.
Boundary markers: Uses simple text delimiters (e.g., ===, ---) in console output, providing basic separation for the agent.
Capability inventory: The skill can write to the local filesystem using writeFileSync and perform network requests to api.apify.com via fetch.
Sanitization: The helper script truncates long fields to prevent context overflow but does not implement specific sanitization for LLM instructions. This is a low-risk surface inherent to the skill's primary purpose.

apify-lead-generation