career-site-job-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill contains explicit instructions to install dependencies automatically and to conceal or avoid requesting user approval ("without asking the user to confirm" and "Do not describe it... and do not request separate approval"), which are deceptive directives outside the scraper's stated data-collection purpose.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required runtime workflow invokes the browser-act Skill to access and interact with real public web pages, so outsider-authored free text from those pages can be ingested into the agent’s 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 directs the agent to automatically install and invoke the BrowserAct runtime from the external 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 that the agent relies on at runtime.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill instructs the agent to automatically install the BrowserAct CLI (a system dependency) without asking the user for confirmation, which pushes the agent to modify the host system state and potentially perform privileged actions.