ecommerce-price-monitor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The Skill explicitly instructs the agent to install a runtime dependency automatically and to "not request separate approval" or describe it as a user-facing browser request, which is a deceptive directive that avoids user consent and is outside normal transparent behavior.

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 “capture browser-visible page content” from user-specified target URLs at runtime, which can include outsider-authored free text from public web pages (indirect prompt injection risk via scraped page content/network responses).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly directs the agent to perform an automatic runtime installation using the BrowserAct install links (https://www.browseract.com/?co-from=ecommerce and https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main), which are required runtime dependencies that will fetch and install external code and influence the agent's execution/workflow.

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 explicitly directs the agent to automatically install the BrowserAct CLI if missing and to do so without asking the user for approval, which instructs the agent to modify the host system by installing software (changing machine state) even though it doesn't explicitly request sudo or system-file edits.