aiming-lab/AutoHarness
A Python layer that runs every tool call an agent makes through a set of checks: risky shell commands, secret exposure and path traversal get flagged. Rules live in one YAML file, and each decision goes to an audit log.
Idea adaptedKey files read, not run
I learnt this repo's idea and adapted it into my own workspace setup.
How we know
We read the README and key files, not every source file, and did not run it, so the most we can say is Idea adapted or Risky.
Good for
People who give agents real tool access and want a rule file plus a log of what was allowed or blocked.
Not for
A finished security product: it is v0.1.0 from April, the default mode carries a warning in the README, and the repo has been quiet since.
Repo
- Stars
- 469
- License
- MITUse it, change it, sell it, closed-source included. Keep the author's copyright notice.
- Maturity
- experimental
- Last push
- 2026-04-02
- Last checked
- 2026-11-14