Back to skill

Security audit

Teen Phone / Game Screen Addiction Detection | 青少年沉迷手机/游戏行为识别

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because scanners report undeclared account and credential handling, broad and potentially unintended processing of sensitive video, and other behavior that raises concerns beyond its stated monitoring purpose.

Consider the suspicious verdict and the reported credential, identity, and remote-processing behavior before installing, especially if you might use it with minors’ footage. The scan was partial: a referenced local path was missing, so some evidence is incomplete. The scanners report substantial concerns, but do not establish malicious intent.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Findings (25)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied chunk does not implement the declared monitoring workflow and its only substantive method is an unrelated, nonfunctional agent-chat interface. There is no active subprocess execution or camera access in this chunk. Imported base classes and services are not supplied, so their behavior cannot be assessed; the mismatch finding is limited to the visible code.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied chunk contains no camera processing, pose estimation, screen-time accumulation, or posture-alert logic. Absence of those features in a shared utility module alone would not establish a mismatch. However, the implemented persistent identity provisioning, remote account registration, credential-bearing requests, and payment workflow introduce substantive account/service behavior not disclosed by the posture-monitoring description. General formatting, polling, and directory helpers are ordinary supporting details and are not themselves grounds for the finding. The assessment is limited to the supplied chunk; it does not establish that camera-analysis functionality is absent elsewhere.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The supplied chunk is primarily a user-account database component, not a camera-analysis or screen-time monitoring implementation. Generic database persistence could be a supporting detail, but this chunk specifically manages identity records and tokens without any visible connection to posture measurements, screen-time sessions, or alert thresholds. No camera access, pose estimation, duration tracking, or alert generation appears here. This assessment is limited to the supplied chunk; it does not establish that the broader skill lacks those features or that stored information is transmitted externally.

Content

No source excerpt is available for this finding.

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: "smyx-teen-screen-addiction-detection-analysis"
description: "Using fixed cameras at home, study rooms or schools, the system analyzes adolescents' posture while using phones or gaming devices: head pitch angle (downward > 45°) and hand-holding-device posture (hand grasp + bent arm). It counts daily cumulative screen-looking time. | 通过家庭、自习室或学校固定摄像头,分析青少年使用手机或游戏设备的姿势,检测头部低垂角度(俯仰角大于45°)以及手持设备的姿态(手部抓握且手臂弯曲),统计每日累计低头看屏幕的时长。当连续低头时长超过设定阈值(如单�

The request helper attaches service credentials to arbitrary caller-supplied destinations.

High
Category
Excessive Agency
Confidence
99% confidence
Finding

Absolute caller-supplied URLs bypass the base URL, but the helper still attaches service tokens and API keys. A caller able to influence the destination can receive those credentials at an attacker-controlled endpoint, and permitted HTTP URLs can also expose them in transit.

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, file_write, 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.

The default trigger selects teen screen-addiction analysis for any home, study-room, or school fixed-camera video submitted for analysis, regardless of the user's intended task.

Medium
Category
Trigger Abuse
Confidence
96% confidence
Finding

The default trigger treats any submitted home, study-room, or school camera footage as authorization for teen screen-addiction analysis, even when the requested task is unrelated. This can initiate sensitive behavioral profiling and cloud processing of minors without task-specific authorization; the later consent guidance does not constrain this broad trigger.

Content

No source excerpt is available for this finding.

The --export-env-only option promises not to execute analysis, but supplying it still processes the video when an input is provided.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The parser advertises an export-only option that will not run analysis, but the program never checks that option and proceeds with analysis whenever input is supplied. A caller relying on this promise can unintentionally initiate remote processing of sensitive footage of minors, and identity initialization also occurs despite the purported export-only mode.

Content

No source excerpt is available for this finding.

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · skills/smyx_analysis/scripts/skill.py (reported line 28)May include surrounding context.

python
result_json = JsonUtil.parse(result_json_pure_text, result_json_pure_text)

        result_json_common_ai_response = result_json.get("commonAiResponse") if isinstance(result_json,
                                                                                           dict) else result_json
        if result_json_common_ai_response:
            result_json = result_json_common_ai_response

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · skills/smyx_analysis/scripts/skill.py (reported line 33)May include surrounding context.

python
result_json = result_json_common_ai_response

        result_json_health_ai_response = result_json.get("healthAiResponse") if isinstance(result_json,
                                                                                           dict) else result_json
        if result_json_health_ai_response:
            result_json = result_json_health_ai_response

Local file contents are submitted to the analysis API without disclosure that the file will be uploaded.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

For a local path, the code reads the entire file and passes its contents to the remote analysis interface without an upload disclosure or authorization check in this path. Although API use is documented generally, local-file selection is not reliable evidence of informed permission to transfer identifiable footage of minors from private rooms or classrooms.

Content

No source excerpt is available for this finding.

The documented export-only mode still executes video analysis.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The export-only flag is parsed but never tested, so supplying it with a video still reaches the analysis call. This violates an explicit no-analysis expectation and can cause unintended remote processing of private footage, with greater privacy consequences when used for minors.

Content

No source excerpt is available for this finding.

The service exposes general-purpose remote modification and deletion capabilities unrelated to the stated posture-monitoring purpose.

Medium
Category
Excessive Agency
Confidence
86% confidence
Finding

At L077–L095, the service forwards caller-supplied URLs and arguments to HTTP PUT and DELETE operations. General-purpose remote resource modification and deletion are not justified by the manifest's posture detection, screen-time tracking, and intervention-alert functions; this file does not constrain those operations to a relevant monitoring service.

Content

No source excerpt is available for this finding.

The save() docstring promises record creation, but insertion failures trigger updates to existing records.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

Any insertion exception triggers an update by ID and potentially by username or realname, allowing a creation attempt to overwrite an existing record instead of failing. If incoming model data is untrusted or mismatched, this can corrupt user identities and stored credentials; no exploitation path from posture input is established.

Content

No source excerpt is available for this finding.

ai_chat claims to invoke an analysis agent, but the invocation is disabled and no analysis result is returned.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The docstring at L26 explicitly says this method invokes openclaw agent through subprocess, and L33-L34 promise an analysis result or session ID. However, the subprocess invocation is commented out at L61-L66; L68 instead creates an empty dictionary, whose stderr access at L70 raises an exception that L81-L82 suppress, causing the method to return None without performing analysis.

Content

No source excerpt is available for this finding.

FileUtil.open silently truncates existing files without disclosing its destructive behavior.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

Opening a path in 'w' mode immediately truncates any existing file, even before the caller writes data. This generically named helper has no docstring, explanatory comment, confirmation, or user-facing message disclosing that behavior; the exception handler does not disclose successful truncation.

Content

No source excerpt is available for this finding.

HTTP requests can silently register a remote account, an undeclared behavior unrelated to posture analysis.

Medium
Category
Excessive Agency
Confidence
97% confidence
Finding

A routine request can automatically call phoneLogin with silent and register enabled, transmitting the current identity without a separate enrollment decision. This undisclosed account-creation side effect is outside the stated posture-analysis function and is especially concerning in a skill involving adolescents.

Content

No source excerpt is available for this finding.

Ordinary HTTP requests can silently trigger remote account registration and local credential persistence.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The request helper can perform remote registration and persist returned tokens in the local user database without an explicit enrollment or credential-storage step. These hidden side effects expand privacy and credential exposure beyond what users would expect from posture analysis, although unauthorized local access is not demonstrated.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This POST transmits the current identifier as both openId and mobile to a remote login/registration service as an implicit request side effect. The concern is undisclosed identity transmission, not evidence that camera footage is uploaded or that the destination is malicious.

Content

Scanner excerpt · skills/smyx_common/scripts/util.py (reported line 561)May include surrounding context.

python
"source": ConstantEnum.DEFAULT__SKILL_HUB_NAME
            }
            try:
                _response = requests.post(_url, json=_data)
                if _response.status_code == 200:
                    _response_json = _response.json()
                    if _response_json and _response_json.get("success"):

Configuration loading silently creates directories and writes files, including during module import.

Low
Category
Output Handling
Confidence
91% confidence
Finding

When a configuration file is missing, YamlUtil.load creates its parent directory and writes a YAML file without a confirmation, log, docstring, or explanatory comment disclosing this side effect. BaseEnum.init_subclass calls this loader during class creation (L044–L059), so importing the module can modify the filesystem even when the caller only expects to read configuration.

Content

No source excerpt is available for this finding.

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · skills/smyx_common/scripts/dao.py (reported line 243)May include surrounding context.

python
username = getattr(model, "username", None)
            if username:
                column_names = self.__model__.__table__.columns.keys()
                update_data = {key: getattr(model, key) for key in column_names if key != "username"}
                return self.update_by_username(username, **update_data)

            return None

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · skills/smyx_common/scripts/dao.py (reported line 353)May include surrounding context.

python
column_names = self.__model__.__table__.columns.keys()

            for key in column_names:
                value = getattr(model, key)
                setattr(instance, key, value)

            session.commit()

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · skills/smyx_common/scripts/dao.py (reported line 326)May include surrounding context.

python
if filters:
                for key, value in filters.items():
                    query = query.filter(getattr(self.__model__, key) == value)

            if offset:
                query = query.offset(offset)

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · skills/smyx_common/scripts/dao.py (reported line 441)May include surrounding context.

python
if filters:
                for key, value in filters.items():
                    query = query.filter(getattr(self.__model__, key) == value)

            return query.scalar()
        finally:

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · skills/smyx_common/scripts/util.py (reported line 30)May include surrounding context.

python
elif isinstance(cur, dict):
                        cur = cur.get(part, default)
                    else:
                        cur = getattr(cur, part)
                return cur
            except Exception:
                return default