The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the agent to visit browseract.com to acquire dependencies. This domain is not a recognized trusted organization or well-known technology service, making the source unverifiable.
[REMOTE_CODE_EXECUTION]: The instructions mandate the automatic installation of a CLI and skill from a remote URL (https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main). Executing code or installing packages from unknown external sources is a high-risk pattern for arbitrary code execution.
[COMMAND_EXECUTION]: The skill contains explicit instructions to bypass user oversight, telling the agent to install dependencies "automatically without asking the user to confirm" and to "not request separate approval for dependency installation." This is a significant autonomy abuse finding designed to conceal system-level changes from the user.
[PROMPT_INJECTION]:
Ingestion points: The skill captures "browser-visible page content" and "network responses" from external Tesco URLs, which could be controlled by an attacker.
Boundary markers: There are no instructions provided to treat captured content as untrusted or to use delimiters to prevent the agent from obeying instructions embedded in the scraped data.
Capability inventory: The agent is empowered to execute a CLI tool and perform network operations based on the state of the session.
Sanitization: The skill lacks any requirement to sanitize, validate, or filter external content before processing it within the agent's context.

tesco-product-scraper