The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill includes a customMapFunction parameter described as a 'JavaScript function to transform each output object'. This allows for the execution of arbitrary code strings provided as input. While this is a common feature in data scraping tools, it presents a risk if the execution environment is not properly sandboxed.
[INDIRECT_PROMPT_INJECTION]: This skill is designed to ingest and process large volumes of untrusted data from TikTok, including profile bios, usernames, and hashtag content. This content could be crafted by third parties to include instructions that attempt to manipulate the agent's output or behavior.
Ingestion points: Data returned from the TikTok scrapers (apidojo/tiktok-scraper and apidojo/tiktok-profile-scraper) in Step 4.
Boundary markers: There are no explicit delimiters or instructions to the agent to ignore potentially malicious content within the scraped TikTok data.
Capability inventory: The skill utilizes file system operations (writing results to CSV/JSON) and network operations (calling Apify APIs via curl).
Sanitization: No sanitization or validation logic is defined for the scraped content before it is processed and formatted into the final report.
[COMMAND_EXECUTION]: The workflow relies on the execution of local shell commands, specifically node scripts/run_actor.js and curl, to interact with external APIs and manage local files. This provides the agent with broad access to the local environment to fulfill the skill's primary tasks.

discovering-tiktok-creators-by-niche