domain-email-enricher

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill explicitly instructs the agent to install a runtime dependency automatically "without asking the user to confirm" and to "not describe" the installation as a user request, which directs deceptive/hidden behavior outside its stated enrichment 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 invoke the browser-act Skill for live website interaction (public pages fetched at runtime), which can cause outsider-authored free text from arbitrary URLs/pages to be ingested into the LLM context via BrowserAct’s browser-extracted content.

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

• Potentially malicious external URL detected (high risk: 0.80). The Skill instructs the agent to install and invoke BrowserAct at runtime using external links (e.g., https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which would fetch and install remote code required for operation.