Back to skill

Security audit

Pet Body Condition & Health Analysis Skill | 宠物体态健康分析技能

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report account and credential handling, broad network capabilities, and behavior that does not consistently match its pet-health purpose; the review is partial because one referenced path could not be resolved.

Consider avoiding installation until the account, credential, network, and opt-out behaviors are clearly explained and addressed. The scan found no AIG issues, but Skillspector was partial: one referenced path could not be resolved, so the evidence is incomplete.

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 contains no pet-health assessment logic or pet-specific data model. Its substantive purpose is user-account database management, including fields for email, birthday, sex, age, token, and open_token. Database persistence can be a supporting implementation detail, but this chunk provides account and credential management without a visible connection to the declared pet-health functionality. The mismatch concerns these supplied capabilities; the code does not demonstrate network transmission, token use, or malicious behavior.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied chunk does not implement the declared purpose. No pet data processing, condition detection, or health assessment is shown. Although comments describe invoking an external agent, that invocation is disabled and must not be treated as actual command execution. Imported base classes and services are not supplied, so their capabilities cannot be determined; this assessment is limited to the visible code.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The supplied chunk contains no pet-health assessment logic. Ordinary formatting, polling, and request helpers could support the declared skill and are not independently mismatches. However, the automatic remote account-registration workflow, persistent identity and token management, and payment-related behavior add material account-service capabilities absent from the description. The request wrapper also attaches credentials without restricting absolute URLs to the configured service origin. These behaviors occur when the relevant utilities are invoked; the chunk does not establish that they run automatically on import or that credentials have actually been disclosed.

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-body-health-analysis"
description: "Identifies obesity, emaciation, external injuries, skin abnormalities, and abnormal mental states, helping pet owners detect health issues promptly. | 宠物体态健康分析技能,识别肥胖、消瘦、外伤、皮肤异常、精神状态异常,帮助宠物主人及时发现宠物健康问题"
version: "1.0.25"
license: "MIT-0"
---

# 🐕 Pet Body Condition & Health Analysis Skill | 宠物体态健康分析技能
> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询

---

## 🧭 技能概览 | Overview

| 模块 | 内容 |

The request utility can attach service credentials to arbitrary caller-supplied HTTP destinations.

High
Category
Excessive Agency
Confidence
99% confidence
Finding

The utility accepts arbitrary absolute HTTP or HTTPS URLs and then automatically attaches X-Access-Token, X-Api-Key, and Authorization headers. A caller-controlled destination can therefore receive service credentials and identity metadata, while an HTTP destination additionally exposes 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.

History-report lookup automatically activates on generic report requests without requiring pet-health context.

Medium
Category
Trigger Abuse
Confidence
94% confidence
Finding

The automatic trigger includes generic requests such as querying historical reports and displaying report lists, then mandates a cloud lookup without checking that the user means pet-health reports. In a multi-skill assistant this can cause unintended authenticated network activity and disclosure of report information unrelated to the user's request.

Content

No source excerpt is available for this finding.

The documented analysis opt-out flag is ignored, so analysis still runs.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The parser promises that --export-env-only will not execute analysis, but the flag is never checked. When media input is supplied, execution proceeds through identity initialization and analysis despite that explicit opt-out, potentially transmitting private media or incurring service charges.

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 disclosure of the upload.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The code reads the entire local file and passes its contents as a file payload to the analysis service. No prompt, log, docstring, or comment here explains that local video data will be uploaded for processing; the file-reading comment describes only the local read.

Content

No source excerpt is available for this finding.

The --export-env-only option promises not to perform analysis, but the code ignores it and proceeds with analysis when an input is supplied.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The --export-env-only flag explicitly promises to skip analysis, but its parsed value is never used. With an input present, the program initializes identity and invokes video analysis, violating the user's opt-out and potentially causing unwanted media transmission or charges.

Content

No source excerpt is available for this finding.

The service exposes unrestricted remote-resource mutation capabilities unrelated to pet-health analysis.

Medium
Category
Excessive Agency
Confidence
88% confidence
Finding

The http_put and http_delete methods forward caller-supplied URLs and arguments to network helpers, exposing general-purpose remote update and deletion capabilities. Network requests can reasonably support remote pet-health analysis, but arbitrary resource modification and deletion are not justified by the manifest's diagnostic purpose. This file demonstrates the capability, not that destructive requests are actually invoked.

Content

No source excerpt is available for this finding.

The skill includes persistent user-account and credential management unrelated to pet health analysis.

Medium
Category
Excessive Agency
Confidence
92% confidence
Finding

The user model stores token and open_token as ordinary database strings, and the DAO uses a workspace-shared SQLite database without visible credential encryption or restrictive permission enforcement. When populated, these fields expose reusable credentials to anyone able to read that database or its backups; account management being outside the advertised pet-analysis purpose increases the need for disclosure but is not itself proof of maliciousness.

Content

No source excerpt is available for this finding.

The ai_chat docstring claims an agent invocation, but the implementation never invokes an agent or produces analysis.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The docstring at L26 explicitly states that this method invokes openclaw agent through subprocess. However, the subprocess call is commented out at L61-L66, and L68 substitutes an empty dictionary; accessing result.stderr then raises an exception that is caught, leaving the method to return None without performing the documented analysis.

Content

No source excerpt is available for this finding.

FileUtil.open silently truncates existing files without disclosing its destructive write mode.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

Opening a path with mode 'w' immediately truncates any existing file, even before the caller writes content. This generic open helper has no docstring, explanatory comment, confirmation, or user-facing log disclosing that behavior; exception tracing does not disclose successful truncation.

Content

No source excerpt is available for this finding.

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

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

An ordinary request can trigger a phoneLogin call with silent registration enabled, then copy returned tokens into a local user model and save it. This introduces account creation and persistent credential handling without a consent gate in the shown flow, expanding the privacy and credential-exposure risks of a pet-analysis skill.

Content

No source excerpt is available for this finding.

HTTP authentication silently sends the current identity to a remote service and requests account registration.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The authentication helper sends the current identity as both openId and mobile while requesting silent registration, without a consent check in this flow. Depending on configuration, that identity can originate from an API secret or a user identifier, making this an unexpected disclosure and account-creation side effect rather than merely a pet-health request.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This POST transmits the current identity and requests remote account registration as an automatic authentication side effect. External transmission alone is not malicious, but the missing consent boundary and possible use of a configured API secret make this the same privacy issue identified by the registration findings, not an independent exfiltration mechanism.

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 files, including during module import.

Low
Category
Output Handling
Confidence
94% confidence
Finding

YamlUtil.load creates parent directories and writes a YAML file when the requested configuration is missing, without a docstring, explanatory comment, log, or confirmation disclosing this side effect. Because BaseEnum.init_subclass invokes this loader when the enum classes are defined (L053 and L058), 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 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/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/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