twitter-x-follower-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill explicitly instructs the agent to install required dependencies automatically and to hide that action from the user ("do not describe it as a request... do not request separate approval"), which is a deceptive instruction outside normal transparent behavior.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The document instructs deceptive, automatic installation of an external CLI without user consent and encourages harvesting contact info (emails/contacts), which enables covert installation and large-scale data collection—indicative of potentially malicious intent and abuse.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The required workflow invokes the browser-act Skill to access arbitrary live public Twitter/X pages at runtime (public web content category), which can include outsider-authored free text that the agent reads into the LLM context via the browser-extracted page content.

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

• Potentially malicious external URL detected (high risk: 0.90). The Skill explicitly requires installing the BrowserAct runtime at runtime using the provided install links (e.g., https://www.browseract.com/?co-from=lead-generation and https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which would fetch and install remote code as a required dependency and thus can execute remote code during skill execution.