Security risk report for @forgecat/microsoft-azure_skills-azure-rbac v0.0.4
Source Integrity
Low
Profile sourced from Microsoft's official azure-skills repository (https://github.com/microsoft/azure-skills), a trusted first-party source.
Licensed under MIT; metadata and commit hash provided for auditability.
Agent Intent
Low
Content describes legitimate Azure RBAC role-finding and assignment workflows; no instructions to ignore system prompts, exfiltrate credentials, or manipulate the agent.
Guidance on least-privilege role assignment and prerequisites for granting roles reflects standard security best practices, not poisoning.
No hidden instructions to fetch external URLs, install untrusted dependencies, or weaken security controls.
Details
Evidence
Skill description: 'Helps users find the right Azure RBAC role for an identity with least privilege access'
Prerequisites section correctly identifies required permissions (Microsoft.Authorization/roleAssignments/write) and recommends least-privilege role (User Access Administrator)
Permissions
Low
No tools are declared in the profile; the skill references internal Azure documentation and code-generation tools (azure__documentation, azure__extension_cli_generate, azure__bicepschema, azure__get_azure_bestpractices) that are expected to be provided by the host platform.
Described functionality (role lookup, CLI command generation, Bicep code generation) aligns with the stated purpose of assisting with Azure RBAC configuration.
Details
Evidence
No declared tools section; no shell, file_write, file_delete, or other high-risk categories requested.
Tool references are descriptive (azure__documentation, azure__bicepschema) and scoped to Azure RBAC guidance.
MCP Risk
Low
No MCP servers are defined in the profile.
No external binary execution, network access, or filesystem operations declared.
ForgeCat