Figma Slides — the complete, unedited output of the deterministic mcptrustchecker engine v1.13.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.13.0",
"methodologyVersion": "mcptrustchecker-1.13"
},
"target": {
"id": "figma-slides-mcp",
"source": {
"kind": "package",
"origin": "figma-slides-mcp"
},
"server": {
"name": "figma-slides-mcp"
}
},
"grade": "B",
"score": {
"score": 89,
"threatScore": 100,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"kind": "client",
"term": "verification-discount",
"level": "repo",
"label": "publisher verification (public source) — no provenance, but the source is public and inspectable",
"appliedPenalty": 1
},
{
"kind": "client",
"term": "coverage-honesty",
"level": "source",
"label": "inspection depth (source) — how much of the target the scan could see",
"appliedPenalty": 0
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.13"
},
"capability": {
"level": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code",
"untrusted-input, sensitive-source and egress co-exist across tools (toxic-flow surface)",
"untrusted input can reach code execution"
],
"tags": [
"sensitive-source",
"code-exec",
"untrusted-input"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (58 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-FLOW-002",
"title": "Completed toxic-flow trifecta across tools",
"category": "exfiltration",
"severity": "critical",
"confidence": "strong",
"description": "This server (without client built-ins) exposes a complete data-exfiltration chain: render_satori → get_slide_context → batch_operations. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.",
"remediation": "Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.",
"location": {
"kind": "flow",
"name": "render_satori → get_slide_context → batch_operations"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"untrusted": [
"render_satori"
],
"sources": [
"get_slide_context"
],
"sinks": [
"batch_operations",
"render_d3",
"render_rough",
"render_satori"
],
"path": [
"render_satori",
"get_slide_context",
"batch_operations"
],
"edges": [
{
"from": "render_satori",
"to": "get_slide_context",
"kind": "agent-mediated"
},
{
"from": "get_slide_context",
"to": "batch_operations",
"kind": "agent-mediated"
}
],
"wired": false
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"batch_operations\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"batch_operations\" appears to run shell commands or evaluate code (parameter \"cmd\"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "batch_operations"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"render_d3\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"render_d3\" appears to run shell commands or evaluate code (parameter \"script\"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "render_d3"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"render_rough\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"render_rough\" appears to run shell commands or evaluate code (parameter \"script\"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "render_rough"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"render_satori\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"render_satori\" appears to run shell commands or evaluate code (parameter \"script\"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "render_satori"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"untrusted-input",
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"cmd\" on \"batch_operations\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"batch_operations\" takes a command-shaped parameter \"cmd\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "batch_operations",
"field": "inputSchema.properties.cmd"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "cmd"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script\" on \"render_d3\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"render_d3\" takes a command-shaped parameter \"script\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "render_d3",
"field": "inputSchema.properties.script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script\" on \"render_rough\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"render_rough\" takes a command-shaped parameter \"script\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "render_rough",
"field": "inputSchema.properties.script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script\" on \"render_satori\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"render_satori\" takes a command-shaped parameter \"script\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "render_satori",
"field": "inputSchema.properties.script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script"
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"batch_operations\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"batch_operations\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "batch_operations"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"render_d3\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"render_d3\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "render_d3"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"render_rough\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"render_rough\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "render_rough"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"render_satori\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"render_satori\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "render_satori"
},
"data": {
"tags": [
"untrusted-input",
"code-exec"
]
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "critical",
"confidence": "strong",
"untrustedInput": [
"render_satori"
],
"sensitiveSource": [
"get_slide_context"
],
"externalSink": [
"batch_operations",
"render_d3",
"render_rough",
"render_satori"
],
"selfContained": false,
"path": [
"render_satori",
"get_slide_context",
"batch_operations"
],
"pathWired": false,
"description": "A cross-tool exfiltration chain exists: render_satori → get_slide_context → batch_operations."
}
],
"capabilities": [
{
"tool": "start_session",
"tags": [],
"reasons": {}
},
{
"tool": "connection_status",
"tags": [],
"reasons": {}
},
{
"tool": "get_editor_info",
"tags": [],
"reasons": {}
},
{
"tool": "get_slide_grid",
"tags": [],
"reasons": {}
},
{
"tool": "get_slide_context",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"dump\""
]
}
},
{
"tool": "screenshot_slide",
"tags": [],
"reasons": {}
},
{
"tool": "screenshot_all_slides",
"tags": [],
"reasons": {}
},
{
"tool": "create_slide",
"tags": [],
"reasons": {}
},
{
"tool": "clear_slide",
"tags": [],
"reasons": {}
},
{
"tool": "create_node",
"tags": [],
"reasons": {}
},
{
"tool": "set_properties",
"tags": [],
"reasons": {}
},
{
"tool": "delete_node",
"tags": [],
"reasons": {}
},
{
"tool": "clone_node",
"tags": [],
"reasons": {}
},
{
"tool": "reparent_node",
"tags": [],
"reasons": {}
},
{
"tool": "group_nodes",
"tags": [],
"reasons": {}
},
{
"tool": "ungroup_node",
"tags": [],
"reasons": {}
},
{
"tool": "set_text",
"tags": [],
"reasons": {}
},
{
"tool": "set_text_range_style",
"tags": [],
"reasons": {}
},
{
"tool": "get_text_content",
"tags": [],
"reasons": {}
},
{
"tool": "list_fonts",
"tags": [],
"reasons": {}
},
{
"tool": "place_image",
"tags": [],
"reasons": {}
},
{
"tool": "create_slide_row",
"tags": [],
"reasons": {}
},
{
"tool": "duplicate_slide",
"tags": [],
"reasons": {}
},
{
"tool": "delete_slide",
"tags": [],
"reasons": {}
},
{
"tool": "delete_slide_row",
"tags": [],
"reasons": {}
},
{
"tool": "reorder_slides",
"tags": [],
"reasons": {}
},
{
"tool": "move_slide_to_row",
"tags": [],
"reasons": {}
},
{
"tool": "set_slide_transition",
"tags": [],
"reasons": {}
},
{
"tool": "set_slide_skipped",
"tags": [],
"reasons": {}
},
{
"tool": "set_slide_theme",
"tags": [],
"reasons": {}
},
{
"tool": "focus_slide",
"tags": [],
"reasons": {}
},
{
"tool": "set_slides_view_mode",
"tags": [],
"reasons": {}
},
{
"tool": "create_table",
"tags": [],
"reasons": {}
},
{
"tool": "set_cell_content",
"tags": [],
"reasons": {}
},
{
"tool": "get_cell_content",
"tags": [],
"reasons": {}
},
{
"tool": "insert_table_row",
"tags": [],
"reasons": {}
},
{
"tool": "insert_table_column",
"tags": [],
"reasons": {}
},
{
"tool": "delete_table_row",
"tags": [],
"reasons": {}
},
{
"tool": "delete_table_column",
"tags": [],
"reasons": {}
},
{
"tool": "create_shape_with_text",
"tags": [],
"reasons": {}
},
{
"tool": "create_gif",
"tags": [],
"reasons": {}
},
{
"tool": "create_video",
"tags": [],
"reasons": {}
},
{
"tool": "replace_media",
"tags": [],
"reasons": {}
},
{
"tool": "get_node_tree",
"tags": [],
"reasons": {}
},
{
"tool": "get_node_properties",
"tags": [],
"reasons": {}
},
{
"tool": "find_nodes",
"tags": [],
"reasons": {}
},
{
"tool": "get_selection",
"tags": [],
"reasons": {}
},
{
"tool": "set_selection",
"tags": [],
"reasons": {}
},
{
"tool": "get_interactive_elements",
"tags": [],
"reasons": {}
},
{
"tool": "list_themes",
"tags": [],
"reasons": {}
},
{
"tool": "export_node",
"tags": [],
"reasons": {}
},
{
"tool": "set_viewport",
"tags": [],
"reasons": {}
},
{
"tool": "zoom_to_fit",
"tags": [],
"reasons": {}
},
{
"tool": "batch_operations",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"cmd\""
]
}
},
{
"tool": "create_svg",
"tags": [],
"reasons": {}
},
{
"tool": "render_d3",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "render_rough",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "render_satori",
"tags": [
"untrusted-input",
"code-exec"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
],
"code-exec": [
"parameter \"script\""
]
}
}
],
"surfaceDigest": "9478680e84c3b3084a1009fd9c0ce7cc38d9d75d2226c0f7091a20c9ed0f185b",
"stats": {
"tools": 58,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 4,
"medium": 4,
"low": 4,
"info": 0
}
}
}