GPR-010 · high risk

Block a dangerous tool

Block a named tool after a security review determines that it should not execute.

Decision

block

Matcher

tool = dangerous-tool

Reviewed

2026-08-09

Safe test cases

matching synthetic case

tool = dangerous-toolblock

different benign synthetic case

tool = benign-dangerous-toolunmatched

Limitations

  • Use an exact reviewed tool identifier; broad wildcard blocking is intentionally not represented.

Review before applying

This recipe is a starting point, not a universal security policy. Open it in Policy Studio, replace example identifiers where necessary, review scope and blast radius, simulate where supported, and use the normal approval flow before enforcement.

Recipe SHA-256: f71e12efc3d042f5779fa4d53e0367f6a35dc848e7a578c60b63ed9260abb381

When a policy is saved and delivered through Guard Cloud, it uses the existing Guard policy-bundle compiler. If the policy-bundle signing key is configured, that compiler produces an RSA-PSS-SHA256 signed bundle that local Guard verifies before applying.