The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill accepts a customMapFunction parameter, which is described as a JavaScript function string used to transform output objects. This creates an interface for dynamic code execution where user-provided or agent-generated logic is executed during the data processing stage.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the open web.
Ingestion points: Data enters the context through Google Search results, specifically the firm names, website URLs, and snippets returned by the scraper.
Boundary markers: The instructions do not define any specific delimiters or clear instructions to the agent to ignore potentially malicious content within the search snippets.
Capability inventory: The skill has the ability to execute local scripts via node and make network requests using curl to the Apify API.
Sanitization: There is no evidence of sanitization or filtering applied to the search snippets before they are returned to the agent's context.
[EXTERNAL_DOWNLOADS]: The skill communicates with the external Apify API (api.apify.com) and utilizes a specific Apify actor (apidojo/google-search-scraper). These are interactions with a well-known service provider and the resource belongs to the skill's author.
[COMMAND_EXECUTION]: The skill provides instructions for running a local script scripts/run_actor.js using Node.js to interface with the scraper. It also uses curl to perform REST API calls, including the transmission of an APIFY_TOKEN via an environment variable.

finding-law-firms-via-google-search