dev-ai-coding-metrics

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly requires web search/web fetch for "Fact-Checking" and "Web Verification" (including 55 curated sources in data/sources.json) and instructs the agent to pull current external facts from public sites/APIs, which means the agent will ingest and act on untrusted third‑party web content as part of its workflow.