Back to skill

Security audit

sn-ppt-doctor

Security checks for vulnerabilities and agentic risk

Overview

The skill provides on-demand PowerPoint diagnostics with disclosed configuration checks and user-controlled online tests.

The inspected files do not substantiate the pre-scan malicious signal. Use trusted companion PPT skills, since configuration loading and online probes delegate to those separately installed helpers. Online probes use configured providers; image generation may incur charges and save an image in your chosen directory.

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
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • 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 (12)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

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

MCP server referenced without pinned version: 'uv tool run --from playwright'.

Medium
Category
MCP Rug Pull
Confidence
65% confidence
Finding

uvx/uv tool run commands without ==version create a rug-pull risk.

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 · ppt_doctor/check_environment.py (reported line 31)May include surrounding context.

python
if not node:
        return None
    try:
        result = subprocess.run(
            [node, "--version"],
            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 · ppt_doctor/check_environment.py (reported line 48)May include surrounding context.

python
if not executable:
        return None
    try:
        result = subprocess.run(
            [executable, "--version"],
            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 · ppt_doctor/check_environment.py (reported line 66)May include surrounding context.

python
if not uv:
        return None
    try:
        completed = subprocess.run(
            [uv, "tool", "list"],
            capture_output=True,
            text=True,

MCP server referenced without pinned version: 'uv tool run --from playwright'.

Medium
Category
MCP Rug Pull
Confidence
65% confidence
Finding

uvx/uv tool run commands without ==version create a rug-pull risk.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'uv tool run --from playwright'.

Medium
Category
MCP Rug Pull
Confidence
65% confidence
Finding

uvx/uv tool run commands without ==version create a rug-pull risk.

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 · ppt_doctor/check_environment.py (reported line 153)May include surrounding context.

python
print(json.dumps(result))
'''
    try:
        completed = subprocess.run(
            [*python_runner, "-c", probe],
            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 · ppt_doctor/check_environment.py (reported line 280)May include surrounding context.

python
'''.replace("__PACKAGES__", json.dumps(required_packages))

    try:
        completed = subprocess.run(
            [node, "-e", probe],
            cwd=export_dir,
            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 · ppt_doctor/check_environment.py (reported line 385)May include surrounding context.

python
def _probe(script: Path, args: list[str], timeout: float) -> dict[str, Any]:
    try:
        result = subprocess.run(
            [sys.executable, str(script), *args],
            capture_output=True,
            text=True,

Tainted flow: 'timeout' from os.environ.get (line 518, credential/environment) → subprocess.run (code execution)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · ppt_doctor/check_environment.py (reported line 385)May include surrounding context.

python
def _probe(script: Path, args: list[str], timeout: float) -> dict[str, Any]:
    try:
        result = subprocess.run(
            [sys.executable, str(script), *args],
            capture_output=True,
            text=True,