twitter-x-post-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill includes explicit, deceptive instructions to install dependencies automatically and to "not describe" installation requests or seek user approval, which are hidden behaviors outside the stated scraping purpose.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to use the BrowserAct CLI to access live public Twitter/X pages at runtime (public web content fetched/scraped from user-supplied target URLs/queries), which can include outsider-authored free text that the LLM may ingest.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to automatically install and invoke the BrowserAct Skill/CLI at runtime using the install link https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main, which is a remote URL the agent would fetch to obtain and execute required runtime code.

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 tells the agent to automatically install the BrowserAct CLI/dependencies without asking the user or requesting separate approval, which directs the agent to modify the host system state (potentially requiring elevated privileges or bypassing user consent).