Back to skill

Security audit

sn-ppt-tools

Security checks for vulnerabilities and agentic risk

Overview

The skill provides proportionate presentation tools with disclosed provider credentials, external requests, and confined image output.

Use trusted HTTPS provider endpoints and send only presentation content approved for those services. Image-generation prompts leave your computer despite the absence of a separate privacy warning. For tighter credential scope, set SN_PPT_ENV_FILE to a dedicated configuration file containing only the needed settings.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (10)

Tainted flow: 'timeout' from os.environ.get (line 82, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/fetch_image.py (reported line 88)May include surrounding context.

python
max_bytes = int(
            os.environ.get("SN_PPT_MAX_IMAGE_BYTES", str(DEFAULT_MAX_BYTES))
        )
        with request.urlopen(req, timeout=timeout) as response:
            content_type = response.headers.get("Content-Type", "")
            data = response.read(max_bytes + 1)
        if len(data) > max_bytes:

Tainted flow: 'timeout' from os.environ.get (line 118, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/image_generate.py (reported line 124)May include surrounding context.

python
os.environ.get("SN_PPT_TOOL_TIMEOUT_SECONDS", str(DEFAULT_TIMEOUT_SECONDS)),
        )
    )
    with request.urlopen(req, timeout=timeout) as response:
        raw = response.read().decode("utf-8", errors="replace")
    data = json.loads(raw)
    if not isinstance(data, dict):

Tainted flow: 'timeout' from os.environ.get (line 140, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/image_generate.py (reported line 147)May include surrounding context.

python
)
    )
    max_bytes = int(os.environ.get("SN_PPT_MAX_IMAGE_BYTES", str(DEFAULT_MAX_BYTES)))
    with request.urlopen(req, timeout=timeout) as response:
        data = response.read(max_bytes + 1)
    if len(data) > max_bytes:
        raise ValueError(f"generated image exceeds {max_bytes} bytes")

Tainted flow: 'timeout' from os.environ.get (line 70, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/image_search.py (reported line 73)May include surrounding context.

python
timeout = float(
        os.environ.get("SN_PPT_TOOL_TIMEOUT_SECONDS", str(DEFAULT_TIMEOUT_SECONDS))
    )
    with request.urlopen(req, timeout=timeout) as response:
        raw = response.read().decode("utf-8", errors="replace")
    data = json.loads(raw)
    if not isinstance(data, dict):

Tainted flow: 'timeout' from os.environ.get (line 96, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/web_search.py (reported line 99)May include surrounding context.

python
timeout = float(
        os.environ.get("SN_PPT_TOOL_TIMEOUT_SECONDS", str(DEFAULT_TIMEOUT_SECONDS))
    )
    with request.urlopen(req, timeout=timeout) as response:
        raw = response.read().decode("utf-8", errors="replace")
    data = json.loads(raw)
    if not isinstance(data, dict):

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/env_config.py (reported line 34)May include surrounding context.

python
if explicit:
        return Path(explicit).expanduser().resolve(), "SN_PPT_ENV_FILE"
    if os.environ.get("OPENCLAW_SHELL", "").strip():
        return (Path.home() / ".openclaw" / ".env").resolve(), "openclaw"
    return (Path.home() / ".hermes" / ".env").resolve(), "hermes"

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/env_config.py (reported line 35)May include surrounding context.

python
return Path(explicit).expanduser().resolve(), "SN_PPT_ENV_FILE"
    if os.environ.get("OPENCLAW_SHELL", "").strip():
        return (Path.home() / ".openclaw" / ".env").resolve(), "openclaw"
    return (Path.home() / ".hermes" / ".env").resolve(), "hermes"


def _parse_value(raw: str) -> str:

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · scripts/image_generate.py (reported line 104)May include surrounding context.

python
prompt = str(args.prompt or "").strip()
    if not prompt:
        raise ValueError("prompt is empty")
    return prompt


def _post(url: str, key: str, payload: dict[str, Any]) -> dict[str, Any]:

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

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.

Image-generation instructions omit a privacy warning about transmitting presentation prompt content to an external service.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The image-generation workflow sends prompt-file content to a configured service without explicitly warning that presentation material leaves the host. Because this is an agent-invoked fallback rather than a separate user-facing workflow, confidential presentation content could be transmitted without informed authorization.

Content

No source excerpt is available for this finding.