Back to skill

Security audit

Mental Health Analysis Tool | 心理健康分析工具

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because scanners report privacy and consent concerns around video uploads and remote account setup, along with mismatches between its advertised analysis and the supplied implementation.

Consider avoiding installation until you can verify what data is sent to the remote service, what identity and credentials are stored, and whether analysis can run when you choose an export-only mode. The skill’s advertised analysis capability is also inconsistent with what scanners say the visible implementation provides. Coverage was partial because a referenced path was missing, so the scan does not fully resolve the uncertainties.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
Findings (21)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

The supplied code is generic skill scaffolding with a disabled and broken agent-call helper, not an implementation of the declared mental-health analysis functionality. No active subprocess execution or other undeclared external action is visible. Imported base classes and API services are not supplied, so their capabilities cannot be assessed; this finding is limited to the visible code.

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: "psychology-analysis"
description: "Analyzes human mental health and psychological behavior, supports identifying common psychological problem tendencies through video analysis, and provides structured mental health analysis reports and improvement suggestions. | 心理健康分析工具,针对人的心理健康和心理行为进行分析,支持通过视频分析识别常见心理问题倾向,提供结构化心理健康分析报告和改善建议"
version: "1.0.24"
license: "MIT-0"
---

# 🧠 Mental Health Analysis Tool | 心理健康分析工具
> **智能分析中枢** · 图片/视频智能分析 · 结�

The analysis workflow lacks a user-facing privacy warning about remote processing of sensitive video and cloud-linked mental-health reports.

High
Category
Output Handling
Confidence
94% confidence
Finding

The workflow automatically associates an identity and initiates analysis without clearly warning that local video leaves the device and mental-health reports are cloud-linked. References to APIs and cloud history provide partial notice, but not informed authorization for disclosing identifiable video and highly sensitive inferred health information.

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 documented export-only mode still performs mental-health analysis.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The parser advertises that --export-env-only will not execute analysis, but the parsed flag is never checked. When supplied with a valid input, a supposedly non-processing invocation proceeds into analysis, potentially transmitting sensitive video without the caller's authorization for that operation.

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 that the file will be uploaded.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The local-file branch reads the complete video and supplies it as an upload to the analysis API without a visible disclosure or consent gate. In a mental-health workflow, that can expose identifiable imagery and sensitive personal context to a remote processor when the user may expect local processing.

Content

No source excerpt is available for this finding.

The documented no-analysis mode still invokes video analysis.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The --export-env-only flag promises not to run analysis but is ignored after parsing. With a valid video input, the program still invokes the analysis workflow, violating the caller's explicit no-analysis choice and potentially disclosing sensitive video.

Content

No source excerpt is available for this finding.

The documented record-creation operation can silently overwrite an existing user record.

Medium
Category
Excessive Agency
Confidence
95% confidence
Finding

Any insertion exception triggers an update by ID and then a fallback update matching username or realname, without verifying ownership or limiting writable fields. A colliding record can therefore overwrite an existing user's identity fields or stored tokens, potentially corrupting the account association used for sensitive health reports; external exploitability depends on caller access.

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 states that this method invokes openclaw agent through subprocess. However, both the command arguments and subprocess invocation are commented out (L48–L66); the replacement empty dictionary at L68 causes the attribute access at L70 to fail, and the exception handler suppresses the error and implicitly returns None. This contradicts the documented analysis operation rather than merely omitting an implementation detail.

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 erases existing contents, even before the caller writes anything. This generically named helper has no docstring, comment, confirmation, or user-facing notice explaining that behavior; its exception handler only runs after a failure.

Content

No source excerpt is available for this finding.

The analysis request wrapper silently registers remote user accounts and persists their identities and authentication tokens, beyond the manifest's stated mental-health analysis scope.

Medium
Category
Excessive Agency
Confidence
88% confidence
Finding

At L550-L561, the wrapper posts to /sys/phoneLogin with both silent=1 and register=1, using the current identity as openId and mobile. When authentication tokens are missing, L589-L604 automatically invokes this account-provisioning flow and saves the returned user and tokens locally; this creates persistent account state rather than merely authenticating an explicitly configured analysis request.

Content

No source excerpt is available for this finding.

HTTP requests can silently register a remote account and persist returned authentication tokens.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

When tokens are unavailable, the generic request helper sends the current identity to a separate login endpoint with registration enabled, then saves returned user information and tokens locally. The registration request and credential persistence have no explanatory comment, docstring, confirmation, or user-facing disclosure, and these side effects go beyond merely performing the caller's requested HTTP operation.

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"):

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

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 any log, prompt, comment, or docstring disclosing this side effect. BaseEnum.init_subclass invokes this loader during class definition (L052–L058), so importing the module can modify the filesystem without an explicit save request.

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