Skip to content

fix(governance): agent argument named "tool" bypasses the sensitive-tool approval gate #28

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
sxyrxyy wants to merge 1 commit into from
Closed

fix(governance): agent argument named "tool" bypasses the sensitive-tool approval gate #28

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion src/agentegrity/adapters/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -712,7 +712,12 @@ def _handle_pre_tool_use(self, data: dict[str, Any]) -> dict[str, Any]:

self._append_capped(
self._buffer.tool_calls,
{"tool": tool_name, "type": "tool_call", **tool_input},
# Spread the agent-supplied arguments FIRST so the trusted
# "tool"/"type" fields always win. This dict becomes
# context["action"], which GovernanceLayer's GOV-001 checks
# against the sensitive-tool set; letting an argument named
# "tool" override the real name would bypass that gate.
{**tool_input, "tool": tool_name, "type": "tool_call"},
"tool_calls",
)
self._buffer.tool_usage[tool_name] += 1
Expand Down
Loading