Primr — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "primr",
"source": {
"kind": "package",
"origin": "primr"
},
"server": {
"name": "primr"
}
},
"grade": "A",
"score": {
"score": 93,
"threatScore": 100,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "client",
"term": "capability-exposure",
"level": "high",
"label": "capability blast radius (high) — client exposure if the model is manipulated",
"appliedPenalty": 6
},
{
"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-1.9"
},
"capability": {
"level": "high",
"reasons": [
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"sensitive-source",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (18 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-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (src/primr/output/skills_generator.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/primr/output/skills_generator.py:103`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "src/primr/output/skills_generator.py"
},
"evidence": "\\b[^\\n]{0,80}(?:~/\\.ssh|id_rsa|\\.env|credentials|secrets?)\", re.I, ), re.compile(r\"\\bcurl\\b[^\\n]{0,200}\\",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "src/primr/output/skills_generator.py",
"line": 103,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/primr/core/cli.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/primr/core/cli.py:158`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "src/primr/core/cli.py"
},
"evidence": "try: result = subprocess.run( [\"ollama\", \"list\"], capture_output=True, tex",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/primr/core/cli.py",
"line": 158,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/primr/core/cli_init.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/primr/core/cli_init.py:137`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "src/primr/core/cli_init.py"
},
"evidence": "ubprocess result = subprocess.run( [sys.executable, \"-m\", \"playwright\", \"install\", \"chromium\"], che",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/primr/core/cli_init.py",
"line": 137,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/primr/core/cli_update.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/primr/core/cli_update.py:104`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "src/primr/core/cli_update.py"
},
"evidence": "try: result = subprocess.run( method.upgrade_command, check=False, ) excep",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/primr/core/cli_update.py",
"line": 104,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/primr/data/scraping/stealth_browser.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/primr/data/scraping/stealth_browser.py:268`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "src/primr/data/scraping/stealth_browser.py"
},
"evidence": "try: result = subprocess.run( [sys.executable, \"-m\", \"patchright\", \"install\", \"chromium\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/primr/data/scraping/stealth_browser.py",
"line": 268,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/primr/output/output_utils.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/primr/output/output_utils.py:459`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "src/primr/output/output_utils.py"
},
"evidence": "None try: subprocess.run( [ soffice, \"--headless\",",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/primr/output/output_utils.py",
"line": 459,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/primr/output/report_assembler.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/primr/output/report_assembler.py:309`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "src/primr/output/report_assembler.py"
},
"evidence": "try: subprocess.run( [ \"soffice\",",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/primr/output/report_assembler.py",
"line": 309,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"primr\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "primr"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "query_roadmap",
"tags": [],
"reasons": {}
},
{
"tool": "get_hypotheses",
"tags": [],
"reasons": {}
},
{
"tool": "save_hypothesis",
"tags": [],
"reasons": {}
},
{
"tool": "estimate_skill_pack",
"tags": [],
"reasons": {}
},
{
"tool": "generate_skill_pack",
"tags": [],
"reasons": {}
},
{
"tool": "ping",
"tags": [],
"reasons": {}
},
{
"tool": "estimate_run",
"tags": [],
"reasons": {}
},
{
"tool": "estimate_strategy",
"tags": [],
"reasons": {}
},
{
"tool": "research_company",
"tags": [],
"reasons": {}
},
{
"tool": "generate_strategy",
"tags": [],
"reasons": {}
},
{
"tool": "check_jobs",
"tags": [],
"reasons": {}
},
{
"tool": "run_qa",
"tags": [],
"reasons": {}
},
{
"tool": "doctor",
"tags": [],
"reasons": {}
},
{
"tool": "clear_jobs",
"tags": [],
"reasons": {}
},
{
"tool": "cancel_job",
"tags": [],
"reasons": {}
},
{
"tool": "wait_for_status_change",
"tags": [],
"reasons": {}
},
{
"tool": "show_usage",
"tags": [],
"reasons": {}
},
{
"tool": "delegate_to_agent",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "48189f8b14701b676aaa1ace1ac70d5054329604130c3e0ec0b34d3e4e8711ab",
"stats": {
"tools": 18,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 7,
"medium": 0,
"low": 0,
"info": 1
}
}
}