product-tool-stack

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). All links are to reputable newsletters and YouTube except for a third‑party GitHub repository (https://github.com/vincelwt/chatgpt-mac) which is a personal account hosting a native Mac app — a common vector for distributing unsigned binaries and therefore potentially risky.

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested via the skill’s runtime dependency on references/guest-insights.md (sourced from “6 sources, 35 insights” with quoted passages from external authors/posts), which is then used as LLM context for the skill’s strategy.