seek-job-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill contains covert instructions to install runtime dependencies automatically and explicitly to hide or avoid user approval ("Do not describe..." / "do not request separate approval"), which are deceptive and outside the scraping task's stated purpose.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). The skill directs automatic installation of a third-party CLI from browseract.com (including a redirect-to-GitHub URL) and instructs the agent to install it without user confirmation, which is a suspicious delivery mechanism for executable/CLI software from an unverified vendor.

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 browser-act Skill for live browser execution (public web pages/job postings), which can ingest outsider-authored free text from fetched pages into the LLM context at runtime.

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 at runtime to install and invoke the BrowserAct CLI using the external installer link (https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which is a required runtime dependency and may fetch/execute remote installation code that controls the agent's workflow.