twitter-x-list-member-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The Skill includes explicit, deceptive runtime instructions to install dependencies automatically without user confirmation and to conceal that action (e.g., "do not describe it as a request for the user to open their browser"), which are hidden/undisclosed behaviors outside the Skill's stated data-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 invoke the runtime browser-act Skill to access and extract data from public Twitter/X pages (outsider-authored free text via live browser scraping), which would be ingested into the LLM context through BrowserAct’s page-reading/extraction.

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

• Potentially malicious external URL detected (high risk: 1.00). The Skill requires and instructs automatic installation/use of the BrowserAct runtime from 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 at runtime, which is a required external fetch that can install/execute code and control agent behavior.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill explicitly directs the agent to automatically install the BrowserAct CLI and dependencies without asking the user for confirmation and to treat them as required runtime dependencies, which instructs the agent to modify the host system (install software) and could lead to unauthorized changes or require elevated privileges.