Back to skill

Security audit

Cat & Dog Health Diagnostic Analysis Tool | 猫狗宠物健康诊断分析工具

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this pet video analysis skill suspicious because it reports undeclared behavior and options that may still trigger analysis or remote data handling.

ClawScan's recommendation is DO_NOT_INSTALL. Before reconsidering, verify that export-only requests cannot analyze or upload video, that remote processing and account registration are clearly disclosed, and that history lookup and file changes are limited to what you expect. The verdict is suspicious, not a claim that the author is malicious.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
Findings (20)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The video-analysis commands align with the declared purpose, and output formatting and file saving are supporting features. However, historical-report listing and its separate activation keywords extend beyond the described video-input workflow. The supplied chunk documents these commands but does not expose their implementation, so no additional API, storage, or data-access behavior can be verified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The primary video-analysis workflow aligns with the description, but account-associated history retrieval is an additional capability not disclosed there. Identity resolution and saving reports are supporting implementation details, not separate mismatches. The actual upload, server communication, and pet-health analysis occur in imported code that was not supplied, so those internals cannot be verified from this chunk.

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-analysis"
description: "Triggers when a user provides a video URL or file of a pet (cat/dog/bird) for analysis; supports local video uploads or network URLs to call server-side APIs for health checks, analyzing features like fur, body, and face to identify potential diseases and generate a Pet Safety Guardian health report. | 猫狗宠物健康诊断分析工具,当用户提供猫/狗/鸟等宠物的视频 URL 或文件需要分析时,触发本技能进行宠物健康诊断分析;支持通过上传本地视频或网络视频 URL,调用服务端 API 进行宠物健康检查,分析毛发、身�

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 documented export-only mode does not prevent video analysis.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The parser accepts an option explicitly promising no analysis, but execution never checks it. When accompanied by an input, the command still invokes the analysis workflow, potentially uploading private video despite the caller selecting a non-analysis 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 video contents are submitted to the analysis API without disclosing the upload.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The code reads the entire local input file and passes its contents to the analysis API as a file attachment. There is no confirmation, user-facing notice, or comment explaining the transmission; the comment only describes reading the file, and requesting analysis does not inherently disclose remote processing of potentially private video.

Content

No source excerpt is available for this finding.

The --export-env-only option promises not to execute analysis, but the code still runs it.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The export-only option is parsed but never used to stop execution. Supplying it with a video input still invokes remote analysis, violating the stated no-analysis behavior and potentially transmitting private media unexpectedly.

Content

No source excerpt is available for this finding.

ai_chat claims to invoke the OpenClaw agent for analysis, but the invocation is disabled and no analysis occurs.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The docstring at L26 explicitly states 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 empty dictionary at L68 causes an attribute access failure at L70, which is caught without returning a result. This contradicts the documented analysis behavior rather than merely changing an implementation detail.

Content

No source excerpt is available for this finding.

FileUtil.open silently truncates existing files.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The generic open helper always uses mode 'w', which immediately erases an existing file's contents. There is no confirmation, action log, docstring, or comment disclosing this destructive behavior.

Content

No source excerpt is available for this finding.

HTTP requests can silently trigger remote account registration.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

An ordinary API request can implicitly invoke '/sys/phoneLogin' with both 'silent' and 'register' enabled, transmitting the selected identity and potentially creating a persistent remote account without a separate enrollment decision. Although remote processing is expected for this pet-analysis skill, account creation is a distinct side effect; additionally, the caller can select API_SECRET_KEY as the username, causing a credential to be copied into identity fields that may receive different logging and retention treatment.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

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"):

The automatic history-query triggers include a generic phrase without a pet-health scope requirement.

Low
Category
Trigger Abuse
Confidence
96% confidence
Finding

The generic history-query phrase can activate a mandatory cloud report lookup even when the user means an unrelated type of report. This can unnecessarily access and display pet-report history in an unintended context, although it does not by itself demonstrate cross-user access.

Content

No source excerpt is available for this finding.

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

Low
Category
Output Handling
Confidence
92% confidence
Finding

YamlUtil.load creates the parent directory and writes a configuration file when the requested path is missing, without a log, prompt, docstring, or explanatory comment. BaseEnum.init_subclass invokes this loader as classes are defined (L044–L059), so merely importing the module can modify the filesystem despite the operation being presented as a load.

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