etsy-keyword-research

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The skill includes explicit instructions to automatically install a dependency without user confirmation and to "not describe" the installation as a user-facing request (SKILL.md:41-47), which instructs the agent to hide operational behavior and bypass user consent — a deceptive directive outside the stated research 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 real browser pages” and “capture browser-visible page content” from user-specified Etsy/public URLs at runtime, which can include outsider-authored free text (e.g., product titles/descriptions and page text) that the agent then ingests 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 instructs the agent to automatically install and invoke the BrowserAct CLI at runtime using the provided 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 means the agent will fetch and execute external code from those URLs to control its runtime behavior.