Back to skill

Security audit

Email CRM

Security checks for vulnerabilities and agentic risk

Overview

ClawScan’s verdict is benign with medium confidence: most dimensions are rated okay, while the skill’s tool scope is unclear and the scan has limited coverage gaps.

The verdict is benign, but benign does not mean risk-free. Consider the unclear tool scope and the reported publishing command before installing. Skillspector’s analysis is partial: it inspected all listed components, but two references in SKILL.md could not be resolved, so the evidence is incomplete.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (10)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command performs skill publication, an external distribution operation not covered by the declared local CRM purpose. It contains no SQLite ledger operations or contact-management behavior. Although located in README.md, the command's behavior, if executed, is publication rather than CRM maintenance.

Content

No source excerpt is available for this finding.

Env Variable Harvesting

High
Category
Data Exfiltration
Confidence
60% confidence
Finding

Code enumerates, copies, or searches environment variables for secrets. Bulk environment access can collect credentials unrelated to the skill's stated purpose.

Content

Scanner excerpt · tests/test_email_crm.py (reported line 141)May include surrounding context.

python
def test_default_database_is_per_user_and_independent_of_cwd(self):
        data_home = Path(self.temp.name) / "private-data"
        env = os.environ.copy()
        env.pop("EMAIL_CRM_DB", None)
        env["XDG_DATA_HOME"] = str(data_home)
        working_a = Path(self.temp.name) / "a"

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/test_email_crm.py (reported line 27)May include surrounding context.

python
self.temp.cleanup()

    def invoke(self, script, *args, expected=0, stdin=None):
        result = subprocess.run(
            [sys.executable, str(SCRIPTS / script), "--db", self.db, *args],
            input=stdin,
            capture_output=True,

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/test_email_crm.py (reported line 93)May include surrounding context.

python
before = Path(self.db).read_bytes()
        before_files = sorted(path.name for path in Path(self.temp.name).iterdir())

        result = subprocess.run(
            [sys.executable, str(SCRIPTS / "init_email_crm.py"), "--db", self.db],
            capture_output=True,
            text=True,

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/test_email_crm.py (reported line 114)May include surrounding context.

python
conn.execute("INSERT INTO schema_meta VALUES (1, 0, 'legacy')")
        before = Path(self.db).read_bytes()

        result = subprocess.run(
            [sys.executable, str(SCRIPTS / "init_email_crm.py"), "--db", self.db],
            capture_output=True,
            text=True,

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/test_email_crm.py (reported line 150)May include surrounding context.

python
working_b.mkdir()
        outputs = []
        for cwd in (working_a, working_b):
            result = subprocess.run(
                [sys.executable, str(SCRIPTS / "init_email_crm.py")],
                cwd=cwd,
                env=env,

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/test_email_crm.py (reported line 168)May include surrounding context.

python
empty_xdg_env = env.copy()
        empty_xdg_env["XDG_DATA_HOME"] = ""
        empty_xdg_env["HOME"] = str(Path(self.temp.name) / "home")
        result = subprocess.run(
            [sys.executable, str(SCRIPTS / "init_email_crm.py")],
            cwd=working_a,
            env=empty_xdg_env,

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/test_email_crm.py (reported line 182)May include surrounding context.

python
def test_event_requires_real_contact(self):
        self.invoke("init_email_crm.py")
        result = subprocess.run(
            [sys.executable, str(SCRIPTS / "log_email_event.py"), "--db", self.db, "--contact-id", "99", "--event-type", "sent"],
            capture_output=True,
            text=True,

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/test_email_crm.py (reported line 197)May include surrounding context.

python
)
        self.assertEqual(event["event_type"], "queued")
        self.assertEqual(self.fetchone("SELECT metadata_json FROM email_events")[0], '{"a":true,"z":1}')
        result = subprocess.run(
            [sys.executable, str(SCRIPTS / "log_email_event.py"), "--db", self.db,
             "--contact-id", str(contact_id), "--event-type", "sent", "--metadata-json", "{"],
            capture_output=True,