Agent Trust
- Updated June 29, 2026
- tigrohvost/agent-trust
Local pre-action trust boundary for skills, tools, MCP servers, repo helpers and x402-style resources, giving inspectable allow/review/deny checks before sensitive agent actions.
About
agent-trust is a local-only Claude Code plugin that adds a pre-action trust boundary for skills, tools, MCP servers, repository helpers, x402-style resources, and other agent dependencies. It performs inspectable allow, review, or deny checks before sensitive actions run. A solo builder reaches for it to reduce prompt-injection and supply-chain risk from third-party agent dependencies.
- Pre-action allow/review/deny trust checks
- Covers skills, tools, MCP servers and repo helpers
- Local-only, guards against prompt injection
Agent Trust by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
/plugin marketplace add tigrohvost/agent-trustAdd your badge
Show developers this marketplace is listed on Skillselion. Paste this into your README.
| Last updated | June 29, 2026 |
|---|---|
| Repository | tigrohvost/agent-trust ↗ |
What it does
Local pre-action trust boundary for skills, tools, MCP servers, repo helpers and x402-style resources, giving inspectable allow/review/deny checks before sensitive agent actions.
Who is it for?
Builders wanting a review gate before risky agent dependency calls.
Skip if: Users who need fully automated, unattended agent runs.
Plugins in this marketplace
1 plugin - install individually after you add the marketplace.
