Prism Coder

Detected

• Talks to external services14 places

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

  api.github.com, api.ies.ed.gov, api.openai.com, api.search.brave.com, api.semanticscholar.org, api.voyageai.com

• Sends conversation content outward1 places

  Logs or forwards prompts, messages or tool results to a service outside your machine.

• Runs shell commands4 places

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

• Loads code at runtime2 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.

• Contains instructions aimed at AI agents13 places

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

• Passes model output on without checks2 places

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

• Runs unpinned packages at runtime18 places

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

Not detected: reads environment variables in bulk, accesses credential files, uses elevated privileges, installs itself to run later, 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

25 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.