deep-research-pro

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

• Third-party content exposure detected (high risk: 0.95). The skill’s runtime workflow performs public web/news searches via DuckDuckGo and then fetches full page HTML with curl -sL "<url>", stripping tags into readable text that is ingested into the agent for synthesis—i.e., outsider-authored free text from arbitrary web pages.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly fetches arbitrary external pages at runtime using curl (curl -sL "" | python3 -c "…") and then ingests that content into the agent's context for reporting, so any fetched URL (the "" in that curl command) can directly control prompts and output.