mcp-qa
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill involves numerous local shell commands using
pnpmto build, lint, and test the codebase. It also executes a local CLI to simulate agent interactions with the MCP server. - [COMMAND_EXECUTION]: Uses
curlfor basic connectivity checks against a local development server running onlocalhost:5173. - [SAFE]: The skill manages authentication tokens by caching them in
~/.sentry/mcp.json. This is a standard and documented practice for the developer tools being tested and does not represent an unauthorized credential exposure within the intended workflow of the Sentry repository. - [SAFE]: All referenced packages (such as
@sentry/mcp-server) and commands are internal to the vendor's repository and infrastructure, consistent with the developer-focused purpose of the skill.
Audit Metadata