recruiter-profile-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains explicit, deceptive instructions to auto-install the BrowserAct dependency without user confirmation and to conceal that installation (telling the agent not to present it as a browser request), which are hidden/overriding directions outside the scraper's stated data-gathering 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 BrowserAct CLI for “real browser pages” and “live website work,” which at runtime will fetch and read outsider-authored web page text (public web content) into the LLM context via the browser automation workflow.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly directs the agent at runtime to automatically install the BrowserAct Skill/CLI via https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main, which is a runtime fetch used to obtain/execute external installation code that controls the agent's capabilities.