ai-answer-trace

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

• Third-party content exposure detected (low risk: 0.10). The required workflow uses Python scripts to call external AI engine APIs (Claude, ChatGPT, Gemini) with live web search enabled, which ingest outsider-authored web pages and search results into the agent's context.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill contains a dynamic remote fetching instruction that retrieves and follows instructions from an external URL (https://raw.githubusercontent.com/XPOZpublic/xpoz-agent-skills/main/skills/<name>/SKILL.md) at runtime.