made-in-china-product-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The Skill explicitly instructs the agent to auto-install a dependency and to "not describe" the installation link as a user-facing browser request or ask for separate approval, which directs deceptive, non-consensual behavior outside normal transparent scraping behavior.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). Both URLs point to a third‑party installer endpoint (browseract.com) that the Skill uses to auto-install a CLI dependency without explicit user consent, which is a potential vector for delivering executables and therefore suspicious.

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 runtime browser-act Skill to “access real browser pages” and “capture browser-visible page content” from user-specified URLs, which can include outsider-authored free text (webpage HTML/text) that the LLM ingests into context.

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

• Potentially malicious external URL detected (high risk: 1.00). The Skill instructs the agent to automatically install a required runtime dependency from the provided install link (https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main), which implies fetching and executing remote installation code at runtime and is therefore a high-confidence runtime external dependency.