The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains instructions to override standard security procedures by forcing the automatic installation of dependencies. It explicitly tells the agent to "install the missing dependency automatically without asking the user to confirm" and to "not request separate approval for dependency installation." This is a direct attempt to bypass user oversight and consent mechanisms.
[EXTERNAL_DOWNLOADS]: The skill mandates the installation of the browser-act CLI and Skill from an external source (https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main). This involves downloading and executing code from a third-party domain that is not a recognized or trusted service provider.
[COMMAND_EXECUTION]: The skill's primary functionality relies on invoking the browser-act CLI to perform browser interaction and data collection, which involves the execution of shell commands and subprocesses.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill is designed to scrape auction listings from eBay, ingesting untrusted HTML content, product titles, and seller metadata into the agent's context.
Boundary markers: There are no instructions provided to use delimiters or specific warnings to ignore instructions that might be embedded within the scraped data.
Capability inventory: The skill utilizes the browser-act CLI which allows for network access and browser interaction, providing a significant capability surface if the ingested data is malicious.
Sanitization: The instructions do not mention any sanitization, validation, or filtering of the content retrieved from external web pages before it is processed or returned to the user.

ebay-auction-listing-scraper