web-search

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the required runtime workflow explicitly uses web-search/extraction tools (e.g., belt app run tavily/search-assistant and belt app run tavily/extract/exa/*) whose outputs are extracted from outsider-authored web pages or search results and then fed into an LLM prompt for summarization.

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 inference.sh platform at runtime (see "https://inference.sh" and the belt app run commands), which executes remote apps/models that control prompts and behavior, so this external URL is a runtime dependency that can directly control the agent.