threads-search-results-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The skill contains explicit, deceptive runtime instructions to install dependencies automatically and "do not request separate approval" or describe the installation as a user action, which directs the agent to hide installation/consent behavior outside the stated scraping purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The Skill explicitly instructs automatic installation of an external CLI without user confirmation and tells the agent not to request or disclose installation approval, creating a clear supply-chain/stealth-installation risk that can be abused.

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 Threads web pages at runtime and then work with the visible page content/fields it returns, which is outsider-authored free text from public web sources.

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 install and invoke the BrowserAct runtime at runtime using the install URL https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main, which would fetch and execute remote code as a required dependency.