CalvinBackup/CyberStrikeAI
1
0
Fork 0
mirror of https://github.com/Ed1s0nZ/CyberStrikeAI.git synced 2026-09-17 15:12:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

feat: add configurable tool call blocking and monitoring

Browse Source
This commit is contained in:
Ed1s0nZ
2026-09-08 09:44:32 +08:00
parent c70da22de7
commit 6ad9ea2d13
54 changed files with 4635 additions and 152 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1
View File
@@ -126,6 +126,7 @@ CyberStrikeAI connects planning, execution, human oversight, evidence, and repla
### Governance and audit
- 🧑‍⚖️ **Human in the loop** provides approval modes, tool allowlists, audit-agent review, and traceable decisions.
- 🛡️ **Call blocking** under Security adds configurable regex checks before MCP execution, reminder templates, and dry runs, with government-domain protection enabled by default. See [Tool call blocking](docs/en-US/tool-call-guard.md).
- 🔐 **Platform RBAC** supports multiple users, system and custom roles, scoped permissions, ownership, and explicit assignments.
- 🔒 **Security and audit** provide authenticated access, audit logs, SQLite persistence, and operational evidence retention.
- 📄 **Result governance** stores the same capped tool result seen by the agent, protects resume paths from oversized historical output, and adds UI safeguards for large detail views. See [Tool Execution Governance](docs/en-US/tool-execution-governance.md).