meticulous-cli

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly downloads session and replay artifacts and generates AI debug workspaces from them (references/download.md and references/debug.md) and can replay sessions against arbitrary URLs provided to --appUrl (references/simulate.md), meaning user-generated or public web content is fetched and placed into AI-readable context that an agent is expected to read and use to decide next actions, enabling indirect prompt injection.