brand-name-checker

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

• Third-party content exposure detected (high risk: 1.00). The skill's agents explicitly use WebSearch/WebFetch to ingest content from public third-party sites (e.g., twitter.com/x.com, instagram.com, registry.npmjs.org, pypi.org, formulae.brew.sh, packages.debian.org, branddb.wipo.int, euipo.europa.eu, inpi.fr), and the orchestrator directly reads and interprets those results (early-exit logic, risk scoring, and recommendations), which clearly exposes the agent to untrusted user-generated/open web content that can influence subsequent actions.