The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the browser-act CLI and an associated skill from an external repository (github.com/browser-act/skills) via a redirection service (browseract.com). These sources are not recognized as trusted or well-known services.
[REMOTE_CODE_EXECUTION]: The instructions explicitly direct the agent to install missing dependencies automatically "without asking the user to confirm" and state that the agent should "not request separate approval for dependency installation." This behavior is a direct attempt to bypass standard user oversight and consent protocols for software execution and installation.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external Allegro product pages, creating an attack surface for indirect prompt injection.
Ingestion points: The skill captures browser-visible page content, metadata, and network responses from Allegro listings as described in SKILL.md.
Boundary markers: No delimiters, markers, or "ignore embedded instructions" warnings are specified to protect the agent's context from content within the scraped pages.
Capability inventory: The skill utilizes the browser-act tool which provides browser interaction capabilities.
Sanitization: No sanitization, escaping, or validation logic is defined for the captured content before it is processed by the agent or returned to the user.

allegro-product-detail-scraper