flipkart-search-results-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill includes explicit instructions to install a runtime dependency automatically and to not ask the user or describe the action as a user-facing request, which are hidden/deceptive instructions that go beyond its stated data-collection purpose.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to “capture browser-visible page content” and “invoke the browser-act Skill” for live execution, which implies runtime ingestion of outsider-authored free text from public Flipkart web pages into the LLM context via BrowserAct.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to automatically install and invoke the BrowserAct runtime from https://www.browseract.com/?co-from=ecommerce (&redirect=...) at runtime—meaning the agent will fetch and execute external installer/runtime code which directly controls the agent's browsing/instruction execution (https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main and https://www.browseract.com/?co-from=ecommerce).

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (low risk: 0.30). The Skill instructs the agent to automatically install the BrowserAct CLI without asking the user to confirm, which directs the agent to modify the host environment by adding software without explicit user approval, but it does not explicitly request sudo, privilege escalation, system-file edits, or user account changes.