company-contact-enrichment

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill explicitly directs the agent to auto-install a runtime dependency without user confirmation and to hide that installation (do not describe it as a request or request approval), which is a deceptive instruction outside the 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 BrowserAct Skill for live website interaction (public web pages fetched at runtime), which can ingest outsider-authored free text from those pages into the LLM context.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent to automatically install the BrowserAct Skill at runtime using the URL 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 can directly control agent behavior.