trustpilot-review-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains deceptive runtime instructions that tell the agent to install a dependency automatically and to hide/avoid requesting user approval or describing the installation as a user-directed action, which is outside the advertised scraping purpose and instructs concealment of actions.

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 BrowserAct to “access real browser pages” and “capture browser-visible page content” from user-specified Trustpilot URLs at runtime, which can include outsider-authored free text (public review text) that the LLM ingests.

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 CLI at runtime using the install URL (https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main), which would fetch and execute external code that the Skill treats as a required runtime dependency.

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

• Attempt to modify system services in skill instructions detected (medium risk: 0.40). The Skill instructs the agent to automatically install the BrowserAct CLI and missing dependencies without asking the user for confirmation, which directs the agent to perform system-level changes (installation) on the host without explicit consent even though it doesn't explicitly request sudo or other privileged operations.