linkedin-article-newsletter-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The Skill instructs the agent to automatically install BrowserAct without user confirmation and explicitly to hide/avoid describing that installation or requesting approval, which is a deceptive instruction outside the advertised scraping 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 use the BrowserAct CLI to access live LinkedIn pages at runtime and then work with the “visible text”/content it returns, which is outsider-authored free text from public web pages.

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 use the Install BrowserAct URL at runtime to obtain and install the required BrowserAct CLI/Skill, which entails fetching and executing remote installation content (https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main).