research-and-report

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

• Third-party content exposure detected (high risk: 0.80). The skill's toolchain explicitly searches and scrapes public third‑party sources (e.g., octocode's githubSearchCode/githubSearchIssues and firecrawl's search/scrape of tutorials/community content), so the agent will ingest and interpret untrusted, user-generated web content as part of its workflow.