pinterest-trend-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains deceptive runtime-installation instructions that tell the agent to install dependencies automatically and to conceal/avoid asking the user about the installation (override consent), which is outside the advertised 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 invoke the BrowserAct CLI for live browser execution (public Pinterest pages/URLs), which can ingest outsider-authored free text from fetched web content into the LLM context at runtime.

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

• Potentially malicious external URL detected (high risk: 0.80). The Skill explicitly requires installing and invoking BrowserAct at runtime via the provided installer links (https://www.browseract.com/?co-from=social-media and https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which are used to obtain a required runtime dependency and could fetch and execute remote code during installation.

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 explicitly directs the agent to install the BrowserAct dependency automatically without asking the user for confirmation and to resume execution, which encourages the agent to modify the host system (potentially requiring elevated privileges) without user approval.