Back to skill

Security audit

Pet Daily Health Monitoring & Analysis Tool | 宠物日常健康监测分析工具

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this pet-health monitoring skill suspicious because scanners report undisclosed account and credential handling, external transmission of identity and video, and behavior that exceeds or ignores stated choices; review coverage was partial.

The verdict is suspicious, with high overall confidence, and Skillspector recommends not installing. Consider the reported external video and identity transfers, account creation, and credential storage before deciding. Review coverage was partial because a local path-like reference was missing; the separate AIG scan completed without findings, but that does not resolve the reported concerns.

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 (23)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

Generic formatting, polling, and filesystem helpers could reasonably support the declared skill and are not themselves a mismatch. However, this chunk also implements undisclosed identity provisioning, remote account registration, credential persistence, and credential-bearing network requests. In particular, absolute caller-supplied URLs receive the same authentication headers as configured service URLs. These are material behaviors beyond video-based pet-health analysis. No vision processing or health-report generation appears in this chunk, although those functions could exist elsewhere. The assessment concerns capabilities present in the supplied code, not proof that every capability executes when the skill is used.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

Database persistence alone could be a supporting implementation detail. However, this chunk specifically implements user-account and token storage rather than pet observations, health indicators, or reports. Those concrete capabilities are not represented in the declared purpose. No video processing, health analysis, or report generation appears in the supplied chunk. The finding is limited to this code; it does not establish that other parts of the skill lack the declared functionality or that stored data 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: "pet-health-monitoring-analysis"
description: "Based on computer vision, analyzes pet health indicators such as feeding frequency, drinking frequency, excretion status, mental state, vomiting behavior, and limping abnormalities through camera/feeder monitoring videos, promptly detects abnormal pet health conditions, and outputs health monitoring reports. | 宠物日常健康监测分析技能,基于计算机视觉通过摄像头/喂食器监控视频分析宠物的进食频次、饮水频次、排泄状态、精神状态、呕吐行为、跛行异常等健康指标,及时发现宠物异常健康状况,输出健康监测

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 local surveillance-video analysis workflow lacks a clear external-processing privacy notice.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

Although the document mentions API use and cloud history, it does not clearly tell users that locally supplied surveillance footage is uploaded for external processing. Such footage can reveal people, home interiors, and household routines, making the omission materially more sensitive than an ordinary file-processing workflow.

Content

No source excerpt is available for this finding.

Generic history-report phrases automatically trigger pet-health cloud queries.

Medium
Category
Trigger Abuse
Confidence
94% confidence
Finding

The instructions make generic phrases such as querying historical reports automatically trigger a cloud request without requiring pet-health context. In an ambiguous conversation this can retrieve and expose private pet-monitoring history unnecessarily, particularly because identity selection is silent.

Content

No source excerpt is available for this finding.

The --export-env-only option promises not to execute analysis, but the program ignores it and runs analysis anyway.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The parser advertises an export-only mode that performs no analysis, but the parsed flag is never checked. When supplied with an input, the program still initializes identity and invokes analysis, potentially uploading private surveillance footage or incurring charges contrary to the caller's explicit choice.

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 video contents are passed to the analysis API without disclosing the upload to the user.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The implementation reads the entire local video into a multipart file payload and passes it to the analysis API without a disclosure or authorization gate. Home-monitoring videos can contain sensitive information about occupants and routines, so permission to analyze a local file should not automatically imply informed permission to transfer it externally.

Content

No source excerpt is available for this finding.

The --export-env-only option promises not to execute analysis, but does not prevent it.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The export-only option promises not to execute analysis, yet no execution branch checks its value. A caller providing video input alongside this flag still triggers identity initialization and analysis, potentially transferring sensitive media despite explicitly selecting a non-analysis mode.

Content

No source excerpt is available for this finding.

Implements user-profile and credential management beyond the stated pet-health monitoring purpose.

Medium
Category
Excessive Agency
Confidence
88% confidence
Finding

The User model stores personal information and credentials, including email, birthday, token, and open_token (L448–L465), and UserDao exposes inherited CRUD operations over those records (L470–L473). DAO initialization also creates tables and modifies the sys_user schema (L185–L215), introducing account-management capabilities not justified by the manifest's video-based pet-health analysis and reporting scope.

Content

No source excerpt is available for this finding.

ai_chat documents agent execution but never invokes the agent or returns an analysis result.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The docstring at L26 explicitly claims that this method invokes openclaw agent through subprocess, and L33–L34 promise an analysis result or session ID. However, the command and subprocess invocation are commented out (L48–L66); the replacement dictionary at L68 causes the attribute access at L70 to fail, after which the exception handler suppresses the error and the method returns None.

Content

No source excerpt is available for this finding.

FileUtil.open silently truncates existing files without disclosing its write-only behavior.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

Opening a path with mode 'w' immediately erases any existing contents, even before the caller writes data. The generic open method has no docstring, explanatory comment, confirmation, or action log disclosing this destructive behavior; exception tracing does not warn about successful truncation.

Content

No source excerpt is available for this finding.

Health-analysis requests can silently register a remote user account and persist its credentials.

Medium
Category
Excessive Agency
Confidence
95% confidence
Finding

An ordinary HTTP request can automatically invoke phoneLogin with silent=1 and register=1, then persist returned account information and tokens without an explicit enrollment step. Pet-health analysis does not inherently authorize remote account creation, so this hidden side effect creates privacy and credential-lifecycle risks.

Content

No source excerpt is available for this finding.

HTTP requests can silently trigger remote account registration without disclosing that side effect.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The generic request helper contains a reachable registration call that sends an identity to a remote service when credentials are missing. This makes a seemingly routine health-analysis request capable of creating an external account without a separate authorization decision.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This POST automatically transmits the selected identity as both openId and mobile to the configured health service, together with a registration request. The calling code can select API_SECRET_KEY as that identity, so this may also place a credential in account-profile fields; the source does not establish a malicious destination.

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 files and directories without disclosing this side effect.

Low
Category
Output Handling
Confidence
92% confidence
Finding

YamlUtil.load creates the parent directory and writes a YAML file when the requested configuration is absent, without a comment, docstring, prompt, or log explaining the write. BaseEnum.init_subclass invokes this loader during class creation (L044–L059), so merely importing this module can modify the filesystem unexpectedly.

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