email-address-extractor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill instructs the agent to install runtime dependencies automatically without asking the user and explicitly to hide that installation (e.g., "do not request separate approval" / "do not describe it as a request for the user"), which is a deceptive instruction outside the extractor's stated 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 pages fetched at runtime), which can ingest outsider-authored free text from those pages 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 explicitly directs the agent to automatically install a required runtime dependency using https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main, which implies fetching and executing remote installation code at runtime.

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

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The Skill instructs the agent to automatically install the BrowserAct CLI/Skill without user confirmation and to treat it as a required runtime dependency, which encourages the agent to modify the host system state (install software) autonomously.