yahoo-auctions-japan-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains explicit, deceptive instructions to install runtime dependencies automatically and "not request separate approval" or present the action as a user browser request, which instructs the agent to hide and bypass user consent outside the stated scraping 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 runtime browser-act Skill to “capture browser-visible page content” from user-specified Yahoo Auctions Japan URLs, which is outsider-authored free text fetched at runtime and then ingested into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to automatically install a required dependency using the Install BrowserAct link (https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main), which would fetch and install remote code as 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: 0.80). The skill explicitly directs the agent to install the BrowserAct CLI automatically (without asking the user or seeking approval), which instructs the agent to modify the host system by adding software and therefore risks changing machine state without authorization.