Levi Neely
|
537fc2d9d1
|
Remove compliance section from security docs
|
2026-03-18 23:46:48 +01:00 |
Levi Neely
|
0e4848f72f
|
Document: explicitly use anvilmcp sandbox for higher-risk scenarios
|
2026-03-18 23:45:47 +01:00 |
Levi Neely
|
7c7d2de1e3
|
Document default sandbox selection: anvilmcp with fallback to default
|
2026-03-18 23:44:13 +01:00 |
Levi Neely
|
4cf346934d
|
Fix docs: tools path is anvillm/tools, not anvillm/tools/anvilmcp
|
2026-03-18 23:40:16 +01:00 |
Levi Neely
|
c5b96bcac1
|
Update docs: execute_code is the only MCP tool
- Rewrite code execution docs to reflect single-tool model
- Remove obsolete migration guide and testing doc
- Update README, kiro-cli README, BEADS.md MCP sections
- Remove all 'direct tool calls' / 'legacy tools' framing
- Update sandbox-config diagram: roles→sandbox, override→merge
- Add 9P security mitigation: run locally on trusted network
- Regenerate sandbox-config.svg
|
2026-03-18 23:39:23 +01:00 |
Levi Neely
|
e53ce4bb1f
|
Rename read_inbox.sh to check_inbox.sh
Renamed mcptools/read_inbox.sh to mcptools/check_inbox.sh and updated
all references across docs, scripts, and skills.
|
2026-03-18 08:18:20 +01:00 |
Levi Neely
|
2a1d620a31
|
rename 9P endpoint from 'agent' to 'anvillm'
- Update socket path, MountService calls, path prefixes
- Update mcptools, scripts, docs, diagrams, services
- Fix idleSince initialization at session creation
|
2026-03-12 12:13:40 +01:00 |
Levi Neely
|
5f8c41b576
|
Implement MCP code execution pattern (#20)
* Implement MCP code execution pattern
- Add execute_code tool for bash execution in landrun sandbox
- Remove redundant MCP tools (read_inbox, send_message, etc.)
- Implement dynamic tool discovery from ~/.config/anvillm/mcptools/
- Add workspace isolation (~/.cache/anvillm/exec)
- Add security: output limits, concurrency limits, validation, path traversal protection
- Update bot templates (Conductor, Taskmaster) with bash examples
- Update anvillm-communication skill to use execute_code pattern
- Create comprehensive documentation (user guide, migration guide, security guide)
- Add test suite for validation and limitedWriter
- Fix landrun flags: --rox for executables, --env for AGENT_ID passthrough
- Network blocked by default (no --connect-tcp or --unrestricted-network)
Token reduction: 80-99% via progressive tool discovery and subprocess data processing
* Fix code review issues in MCP code execution pattern
- Security: Change security.jsonl permissions from 0644 to 0600
- Bug: Fix limitedWriter to return correct byte count for io.Copy
- Bug: Fix tool schema inconsistency (execute_code requires only 'code')
- Performance: Move whitespace regex to package-level var
- Security: Improve validateCode with regex patterns and normalization
- Cleanup: Remove dead code from main.go and tools.go
- Cleanup: Rewrite shell scripts to use jq for safe JSON construction
- Docs: Fix duplicate sections and JavaScript syntax in bash examples
* Improve code validation security patterns
- Fix rm -rf bypass: allow optional whitespace before /
- Expand rm -rf to block sensitive paths (/home, /var, /usr, etc.)
- Block all network protocols in curl/wget (not just http/https)
- Add test for regex pattern compilation
- Add test cases for tabs, sensitive paths, ftp/file protocols
* Harden shell scripts and improve rate limiting
---------
Co-authored-by: Levi Neely <lkn@darkstar.example.net>
Co-authored-by: Levi Neely <lneely@pascom.net>
|
2026-02-26 14:02:54 +01:00 |