The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains explicit instructions to bypass standard agent confirmation protocols. It directs the agent to "install the missing dependency automatically without asking the user to confirm" and mandates "do not request separate approval for dependency installation," which overrides safety guardrails for software acquisition.
[REMOTE_CODE_EXECUTION]: The skill requires the installation and execution of an external CLI tool from an unverified third-party source during runtime. This creates a critical supply chain risk as the agent is forced to execute code that has not been vetted or authorized by a trusted organization.
[EXTERNAL_DOWNLOADS]: The skill directs the agent to download assets from browseract.com and a third-party GitHub repository (github.com/browser-act/skills). These sources are not on the trusted vendor list and do not qualify as well-known technology services.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a broad data ingestion surface by scraping arbitrary website content provided by the user. Evidence: 1. Ingestion points: 'Capture browser-visible page content' (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Browser execution and network access. 4. Sanitization: Absent. This surface allows malicious instructions embedded in a target webpage to potentially influence the agent's behavior during or after the scraping process.

ecommerce-marketplace-offer-scraper