promptinjection

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This skill is a comprehensive red-team toolkit that explicitly documents and automates techniques for system-prompt extraction, RAG/document poisoning, external data/API scraping, network capture and API-key discovery, multi-stage jailbreaks, and other exfiltration/abuse flows — making it high-risk dual-use content that can be readily abused for unauthorized data exfiltration and system compromise despite its "authorized use only" framing.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The required runtime path for this skill’s workflows (notably Workflows/Reconnaissance.md and Workflows/IndirectInjectionTesting.md) uses browser automation to fetch and extract arbitrary web page/DOM/JS/network content from a user-supplied target URL and to process externally provided documents/URLs, which can include outsider-authored free text that becomes LLM-readable context (e.g., browser extract ... complete DOM structure / browser network-logs / scraping results / uploaded web content).