meticulous-cli

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

• Third-party content exposure detected (high risk: 0.70). The skill's simulate command explicitly replays sessions against the original recorded URL (simulate/SKILL.md "Replay Target") and the debug command bundles replay data and AI context files into workspaces for AI tools (debug/SKILL.md "Workspace Contents"), meaning the agent will ingest and analyze web page content and user-generated session data from arbitrary third-party sites as part of its workflow.