Back to skill

Security audit

text-humanize

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a prose-editing skill with a few low-probability, purpose-related flags; the verdict is benign with high confidence because the reported behavior was assessed as broadly aligned with its stated purpose.

The verdict is benign, but consider whether the reported repository download and the skill's file and shell capabilities fit your needs before installing. The scan inspected all reported components, though benign does not mean risk-free.

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
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The visible behavior is repository retrieval, not prose editing. Nothing in the supplied chunk establishes that cloning this repository supports the declared purpose, so it constitutes an unexplained resource access and capability mismatch. The command does not itself execute the downloaded code, and the repository's contents cannot be inferred from this snippet.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write, 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_preflight.py (reported line 22)May include surrounding context.

python
with tempfile.TemporaryDirectory() as directory:
            path = Path(directory) / 'draft.md'
            path.write_text(text, encoding='utf-8')
            result = subprocess.run([sys.executable, str(SCRIPT), str(path), *args,
                                     *(['--json'] if json_output else [])], capture_output=True, text=True)
            self.assertEqual(path.read_text(encoding='utf-8'), text, 'script must not mutate its input')
        return result, json.loads(result.stdout) if json_output else result.stdout

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_preflight.py (reported line 255)May include surrounding context.

python
self.assertEqual(self.value(data, '最长段落(字)'), 0)

    def test_missing_file_reports_json_error_and_exit_two(self):
        result = subprocess.run([sys.executable, str(SCRIPT), '/nonexistent/text-humanize.md', '--json'], capture_output=True, text=True)
        self.assertEqual(result.returncode, 2)
        self.assertIn('error', json.loads(result.stdout))
        self.assertNotIn('Traceback', result.stderr)

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_preflight.py (reported line 262)May include surrounding context.

python
def test_bad_arguments_exit_two(self):
        for args in (('--para-max', '0'), ('--para-max', '-1'), ('--check', 'typos'), ('--tier', 'unknown')):
            result = subprocess.run([sys.executable, str(SCRIPT), 'unused', *args], capture_output=True, text=True)
            self.assertEqual(result.returncode, 2)