AI agents invoke code_quality_sweep to trigger actions in Git Steer. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes arbitrary SAST (Static Application Security Testing) and linting tools on repository code via GitHub Actions. While SAST tools are generally benign, the tool triggers external execution whose effects depend on the repository contents and tool configurations.
From the tool's definition Tool 'Run linters and SAST tools (ESLint, Ruff, gosec, Bandit) on a repository via GitHub Actions' - explicitly runs external code analysis tools ('Run linters and SAST tools') and 'Auto-detects language stack' to determine execution behavior.
Attacks that exploit this kind of access
Run linters and SAST tools (ESLint, Ruff, gosec, Bandit) on a repository via GitHub Actions. Auto-detects language stack. It is categorised as a Execute tool in the Git Steer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Git Steer MCP server in PolicyLayer and add a rule for code_quality_sweep: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Git Steer. Nothing to install.
code_quality_sweep is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the code_quality_sweep rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for code_quality_sweep. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
code_quality_sweep is provided by the Git Steer MCP server (ry-ops/git-steer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →