consumer-affairs-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 BrowserAct automatically and to "not describe" the installation link as a request for the user to open their browser and to "not request separate approval," which directs deceptive behavior (hiding installation/consent) outside normal transparent scraping duties.

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 “capture browser-visible page content” from public ConsumerAffairs pages at runtime, which is outsider-authored free text (review text and related page content) that can be ingested into the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to automatically install BrowserAct at runtime using the provided install URL (https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main), which would fetch and install/execute remote code that the skill treats as a required runtime dependency.