Export every sfgraph audit finding (governor risks, security gaps, dead code, dangling edges) as a single SARIF 2.1.0 report. The output validates against the OASIS schema and round-trips into GitHub Code Scanning and the VS Code SARIF Viewer. Use this when wiring sfgraph into CI alongside sfdx-s...
AI agents call export_sarif to retrieve information from Sfgraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads and exports existing audit findings into a SARIF report format. It queries/retrieves data (audit findings already computed) and serializes them — no modification, deletion, execution, or financial action occurs. Severity is medium because the SARIF report could expose sensitive security gaps, dead code, and governor risks about the Salesforce org to downstream systems like GitHub Code Scanning.
From the tool's definition Export every sfgraph audit finding ... as a single SARIF 2.1.0 report ... validates against the OASIS schema and round-trips into GitHub Code Scanning and the VS Code SARIF Viewer
Attacks that exploit this kind of access
Export every sfgraph audit finding (governor risks, security gaps, dead code, dangling edges) as a single SARIF 2.1.0 report. The output validates against the OASIS schema and round-trips into GitHub Code Scanning and the VS Code SARIF Viewer. Use this when wiring sfgraph into CI alongside sfdx-scanner/PMD-Apex/CodeScan. It is categorised as a Read tool in the Sfgraph MCP Server, which means it retrieves data without modifying state.
Register the Sfgraph MCP server in PolicyLayer and add a rule for export_sarif: 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 Sfgraph. Nothing to install.
export_sarif is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the export_sarif 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 export_sarif. 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.
export_sarif is provided by the Sfgraph MCP server (ryanstark24/sfgraph). 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 →