The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted metadata, including product names, taglines, and descriptions, from Product Hunt via the Apify API. This data is displayed to the agent without sanitization or boundary markers, which could allow maliciously crafted product entries to influence the agent's behavior in subsequent steps.
Ingestion points: scripts/scrape_producthunt.py fetches items from an Apify dataset.
Boundary markers: None.
Capability inventory: The skill performs network requests and outputs data to the console; no subprocess execution, dynamic code evaluation, or file system writes were identified in the scraping script.
Sanitization: None performed on scraped text fields.
[EXTERNAL_DOWNLOADS]: The skill makes network requests to Apify's official API (api.apify.com) and requires the installation of the standard requests Python library. These interactions with a well-known service and a verified package registry are expected for the skill's stated purpose.

product-hunt-scraper