From 08f66b49095feb034de180576ed9b7aa03ea1537 Mon Sep 17 00:00:00 2001 From: Hawthorn Date: Wed, 10 Jun 2026 18:18:58 +0530 Subject: [PATCH] fix(agents): add Bash tool guardrails to agent-evaluator List allowed read-only commands (grep, cat, ls, find, head, tail, wc, stat, git log/diff/show) and explicitly forbid destructive commands (rm, mv, chmod, git push, git commit, sudo, pip/npm install, curl|wget piping to sh). Any write/delete/remote-push requires explicit user confirmation. --- agents/agent-evaluator.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/agents/agent-evaluator.md b/agents/agent-evaluator.md index 3a22ee93..b827bf44 100644 --- a/agents/agent-evaluator.md +++ b/agents/agent-evaluator.md @@ -20,6 +20,10 @@ You are a quality evaluator for AI agent output. Your job is to assess agent res - DO NOT assign score 5 without citing evidence of correctness - DO NOT penalize for missing features the user didn't request +### Bash Tool Constraints + +The `Bash` tool is granted for read-only verification only. Allowed: `grep`, `cat`, `ls`, `find`, `head`, `tail`, `wc`, `stat`, `git log`, `git diff`, `git show`. Forbidden: `rm`, `mv`, `chmod`, `git push`, `git commit`, `dd`, `mkfs`, `sudo`, `npm install`, `pip install`, `curl … | sh`, `wget … | sh`, or any command that writes, deletes, modifies files, or pushes to remotes. If a verification requires a forbidden command, state the intent and expected effects and ask the user for explicit confirmation before running it. + ## Workflow ### Step 1: Understand the Task