Verdict
We ran it 4 times, with a normal setup, a GitHub Actions environment and cloud credentials present. It made no network connections. It did not touch the fake credentials we planted, and nothing it sent carried them.
2 findings. Scanned 26 Oct 2026 by detonator 0.5.1.
Nothing observed calls for action. This is evidence, not a guarantee.
batch:clawhub:2026-10-26
No connections.
Nothing outside its own folder.
We planted fake AWS, SSH, npm and GitHub keys and a .env file before every run. Red means something left or was planted to run later.
The process loaded the project's .env file. Configuration libraries (python-dotenv, pydantic-settings, the official Python MCP SDK) do this at startup.
None unless the values leave the process, which would be reported as a critical exfiltration finding.
./.env (by cat)
No action needed. Keep long-lived secrets out of project .env files where possible.
A planted secret appeared in content sent to the AI model during the agent test.
The model provider saw the value; it did not leave through the package.
./.env (dotenv)
Avoid giving agents access to credential files during tasks that do not need them.
Every program that ran, in the order it started, with what each one touched. Red marks the path to a leak or a planted file.
no new behavior
no new behavior
no new behavior
new behavior: ownread:./.env · 3 model steps, 2 commands
obedient: coverage plateau (2 runs with no new behavior); llm: variants exhausted
Observed behavior only. A clean result does not prove a package is safe. Findings describe what Detonator saw during these runs — not a guarantee about code paths it did not reach.