chrome-extension-developer

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow and examples (WORKFLOW_REFERENCE.md and SKILL.md) explicitly describe fetching and scanning public GitHub repositories and using background fetch(code like fetchExternalData) and host_permissions (e.g., https://github.com/, https://api.github.com/), meaning the agent ingests untrusted, user-generated third‑party content (SKILL.md files and arbitrary URL responses) that can influence subsequent actions (downloads, parsing, message handling).