bezaleel-stack

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly requires "LIVE RESEARCH" and instructs the agent to perform WebSearch/WebFetch for each detected package (see "CRITICAL: Live Research", "Phase 3: Best Practices Research", and repeated "WebSearch/WebFetch" steps), meaning the agent will fetch and interpret open/public third‑party web content (official docs, blogs, community posts) that directly drives audit findings and recommendations.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires LIVE WebSearch/WebFetch at runtime and uses fetched documentation to drive recommendations and prompts (e.g., WebFetch: https://react.dev/learn and https://react.dev/reference/rsc/server-components), so those external URLs are runtime dependencies that directly control the agent's instructions.