context-hub

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly tells the agent to fetch and treat external documentation/skills from the Context Hub via the third-party CLI "chub" (e.g., "chub search" / "chub get " in SKILL.md), meaning untrusted/third-party content pulled at runtime can directly influence decisions and tool usage.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires and invokes the external "chub" CLI (installed via "npm install -g @aisuite/chub") and uses "chub get " at runtime to fetch remote docs/skills whose content the agent is instructed to treat as authoritative guidance (i.e., remotely fetched content directly controls prompts/instructions).