competitor-landing-page-intent-monitor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains explicit instructions to automatically install a runtime dependency without user confirmation and to hide/avoid describing that installation to the user, which is deceptive behavior outside the stated monitoring 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 use the BrowserAct CLI to access and extract data from user-specified competitor landing page URLs at runtime, which can include outsider-authored free text from public web pages.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires invoking and, if missing, automatically installing BrowserAct at runtime via https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main (and references https://www.browseract.com/?co-from=lead-generation), which instructs the agent to fetch and run external installation/instructions that directly control agent behavior and execute remote code.

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

• Attempt to modify system services in skill instructions detected (low risk: 0.30). The Skill explicitly instructs the agent to automatically install a runtime dependency (BrowserAct CLI) without asking the user for confirmation, which can modify the host system and potentially invoke privileged operations, though it does not explicitly request sudo or direct modification of system files or user accounts.