The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill defines a customMapFunction parameter that accepts a JavaScript string to be executed on the Apify platform. This allows for arbitrary code execution within the remote environment to transform scraping results.
[INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to ingest TikTok comments, which are untrusted external inputs. This creates an attack surface where malicious instructions embedded in comments could influence the agent's behavior during data analysis.
Ingestion points: Scraped comment text, usernames, and reply threads from TikTok video URLs (referenced in SKILL.md).
Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions when presenting the scraped data to the agent.
Capability inventory: The skill has the capability to execute shell commands via node and perform network operations using curl.
Sanitization: No sanitization or filtering of the comment content is described before it is passed to the agent's context.
[COMMAND_EXECUTION]: The skill provides workflows that involve executing shell commands, specifically using node to run a local script (scripts/run_actor.js) and curl to interact with the Apify REST API for task management and data retrieval.
[EXTERNAL_DOWNLOADS]: The skill interacts with the Apify API (api.apify.com) and utilizes a specific Apify actor (apidojo/tiktok-comments-scraper). These are interactions with a well-known service and the author's own infrastructure.

scraping-tiktok-comments