abc/analysis_claude_code
1
0
Fork 0
mirror of https://github.com/shareAI-lab/analysis_claude_code.git synced 2026-09-20 12:13:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor: simplify destructive command matching

Browse Source
This commit is contained in:
Haoran
2026-08-27 00:33:25 +08:00
parent 1293797585
commit 08263f49b3
22 changed files with 507 additions and 3324 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
s04_hooks/README.md
View File

@@ -102,15 +102,12 @@ agent_loop(history)
**PreToolUse / PostToolUse**, hooks before and after tool execution. s03's permission check logic is now wrapped as a PreToolUse hook, plus a logging hook and a large-output reminder:
```python
# PreToolUse: permission check (including the matcher inherited from s03)
# PreToolUse: permission check (s03 logic, moved from loop to hook)
def permission_hook(block):
if block.name == "bash":
command = block.input.get("command", "")
for pattern in DENY_LIST:
if pattern in command:
if pattern in block.input.get("command", ""):
return "Permission denied by deny list"
if contains_destructive_command(command):
return "Potentially destructive command"
if block.name in ("read_file", "write_file", "edit_file"):
path = block.input.get("path", "")
if not (WORKDIR / path).resolve().is_relative_to(WORKDIR):