The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from Twitter, which can contain malicious instructions intended to influence the agent's behavior.
Ingestion points: The skill fetches search results (tweets) from Twitter via the Apify API as described in Step 2 and Step 4.
Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat the scraped tweet content as untrusted data or to ignore instructions embedded within the results.
Capability inventory: The skill has capabilities to write files locally (via run_actor.js saving CSV/JSON) and perform network operations to the Apify API.
Sanitization: The instructions do not mention sanitizing or filtering the tweet data before delivering it to the agent context.
[DYNAMIC_EXECUTION]: The skill exposes a customMapFunction parameter which accepts a JavaScript string to be executed on the Apify platform. While this execution occurs server-side on a well-known service, it provides a surface for injecting dynamic code through the agent's inputs.
[COMMAND_EXECUTION]: The skill relies on shell commands (node, curl) to interact with the Apify platform and manage data. These commands use the APIFY_TOKEN environment variable, following standard secret management practices for the platform.

scraping-tweets-by-keyword