Deja Vu

Detected

• Talks to external services2 places

  Makes outbound requests. The hosts are listed so you can see where data goes.

  api.github.com, api.openai.com

• Runs shell commands27 places

  Spawns processes on your machine. Expected for command, browser and build tools.

• Loads code at runtime1 places

  Uses eval, dynamic imports or encoded payloads, which static review cannot fully follow.

• Reads or writes other agents' configuration3 places

  Touches folders such as ~/.claude, ~/.codex or ~/.cursor, which hold settings and sometimes keys.

• Installs itself to run later4 places

  Writes startup entries, cron jobs or state files that outlive the session.

• Contains instructions aimed at AI agents5 places

  Text in code or agent-facing files that steers a model. Worth reading before you trust it.

• Passes model output on without checks3 places

  Model output reaches HTML, SQL or a shell without validation.

• Runs unpinned packages at runtime9 places

  Executes npx or uvx without a version, so a compromised upstream release would run.

Not detected: reads environment variables in bulk, sends conversation content outward, accesses credential files, uses elevated privileges, matches a known malicious pattern.

Dependencies with known advisories

None found in the lockfiles and manifests checked against OSV.dev.

Left out of the profile

21 pattern matches in documentation, configuration or CI files were recorded but are not part of the profile, because they do not run when the server does. The owner dashboard lists them.