flipkart-review-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.70). The Skill explicitly instructs the agent to install dependencies automatically and to conceal that installation from the user (e.g., "do not describe it as a request" and "without asking the user to confirm"), which is a deceptive instruction outside the user's stated purpose of collecting reviews.

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 use the BrowserAct CLI to access live Flipkart pages and “capture browser-visible page content” at runtime, which would include outsider-authored free text (public web review text) that the LLM ingests into its context.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs the agent to "install BrowserAct" automatically at runtime using the URL https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main, which is a runtime external dependency used to fetch and install required tooling (i.e., execute remote installation), so it directly enables executing remote code.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The Skill instructs the agent to automatically install a required CLI dependency without asking the user for confirmation and to resume execution afterward, which directs the agent to modify the host system (install software) and bypass normal consent flows — a clear instruction that can change machine state and potentially require elevated privileges.