prospect-contact-verification

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill instructs the agent to install a runtime dependency automatically and explicitly tells it not to tell the user or request separate approval, which is a deceptive instruction outside the stated verification purpose.

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 BrowserAct CLI for “live browser pages and execute tasks,” which at runtime can fetch and ingest outsider-authored free text from arbitrary public web pages into the LLM context via the browser workflow.

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 and invoke BrowserAct at runtime using the installer link https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main, which would fetch and execute remote installation code for a required runtime dependency.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill directs the agent to automatically install the BrowserAct CLI and resume execution without asking the user for confirmation, which instructs the agent to modify the host system state (install software) without explicit user consent even though it does not explicitly request sudo or modify specific system files.