Back to skill

Security audit

Fraud Call Identification Analysis Tool | 诈骗电话识别分析工具

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because scanners report a mismatch with its call-fraud purpose, unexpected account and data-handling behavior, and safeguards that may not work as described.

Consider avoiding installation until the purpose mismatch, account and identity handling, external media processing, and export-only behavior have been reviewed. Skillspector reports partial analysis because a local reference could not be resolved, so the evidence is incomplete even though it reports that all listed components were scanned.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/fraud_call_identification.py
Finding

Upstream sender identity is ignored in the default CLI flow

Content
View full analysis

Impact

In the affected shared-workspace configuration, one sender can receive historical analysis reports accumulated under the default account by another sender. Analyses can also be associated with the wrong account.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
Findings (25)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied chunk implements generic scaffolding rather than the declared fraud-analysis workflow. In AgentSkill.ai_chat, result is an empty dictionary, so accessing result.stderr raises AttributeError, which is caught without producing a result. The commented-out subprocess code does not execute. Imported base classes and API services could provide additional functionality, but their behavior is not shown and cannot establish that this chunk delivers the declared purpose. No undeclared external execution or resource access is demonstrated.

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 call-content analysis, scam detection, risk assessment, or report generation. Database initialization and CRUD can be supporting implementation details, but this module specifically manages user profiles and tokens without any visible connection to fraud analysis. Its demonstrated purpose therefore differs materially from the declaration. This assessment is limited to the supplied chunk; no network transmission or token use is shown.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

String, date, polling, and general request helpers can be ordinary supporting implementation details. However, this chunk also implements an undisclosed identity, remote account-registration, credential-persistence, and billing workflow beyond the stated call-analysis function. Its HTTP wrapper can send authentication headers to arbitrary supplied HTTP(S) destinations, although no concrete unauthorized transmission is demonstrated here. These behaviors occur when the relevant helpers are invoked, not simply because their definitions are loaded. The chunk contains no fraud-analysis logic, but that absence alone is not the basis for the mismatch because this is a shared utility module.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The CLI description, input help, progress messages, and history option consistently describe video analysis. The supplied code contains no visible scam-script detection, fraud classification, risk assessment, or anti-fraud report logic; instead, it forwards the input to an imported implementation. That implementation could potentially perform fraud analysis, but its behavior is not supplied, so this cannot be confirmed. Based on the visible interface and operations, the code materially differs from the declared call-fraud analysis purpose and additionally exposes history retrieval. File output and API delegation are supporting implementation details, not independent mismatches.

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: "fraud-call-identification-analysis"
description: "Analyzes incoming call content for multi-dimensional risk, intelligently identifies scam scripts, determines if a call is fraudulent, assesses risk levels, and generates an Anti-Fraud Guardian analysis report. | 诈骗电话识别分析工具,针对来电通话内容进行多维度风险分析,智能识别诈骗话术,判断是否为诈骗电话并评估风险等级,输出反诈卫士分析报告"
version: "1.0.25"
license: "MIT-0"
---

# 📞 Fraud Call Identification Analysis Tool | 诈骗电话识别分析工具
> **智能分析中枢** · 图片/视频智能分析 ·

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 analysis workflow lacks a privacy warning before sending call content to an external API.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The workflow automatically processes local call recordings or transcripts through a cloud API without an explicit pre-upload privacy notice or consent checkpoint. Call content can contain financial details, identifiers, and third-party speech, making undisclosed external processing particularly sensitive in this context.

Content

No source excerpt is available for this finding.

The documented export-only mode does not prevent call analysis.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The parser advertises that --export-env-only prevents analysis, but the parsed flag is never checked. With valid input, execution still initializes identity and invokes analysis, potentially transmitting sensitive call content despite an explicit 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 passed to the analysis API without disclosure that they will be uploaded.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The implementation reads the complete local file and supplies its contents to the analysis API without a disclosure or authorization checkpoint in this path. Users requesting analysis may not understand that private recordings or videos leave the local environment.

Content

No source excerpt is available for this finding.

The documented export-only mode does not prevent analysis.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The --export-env-only option promises not to analyze content, yet no branch checks it before identity initialization or analyze_video. A user relying on this mode can inadvertently initiate external processing of private media.

Content

No source excerpt is available for this finding.

The service exposes unrestricted HTTP PUT and DELETE capabilities beyond the stated call-analysis purpose.

Medium
Category
Excessive Agency
Confidence
88% confidence
Finding

At L077–L081 and L091–L095, the service forwards caller-supplied URLs and arguments to HTTP PUT and DELETE operations. These general-purpose remote modification and deletion capabilities are not justified by the manifest's scope of analyzing call content and generating fraud-risk reports; unlike requests to an analysis backend, they are not constrained to that workflow.

Content

No source excerpt is available for this finding.

The skill includes persistent user-profile and authentication-token management unrelated to its stated call-analysis purpose.

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

The User model stores personal information and authentication material, including email, birthday, token, and open_token, and UserDao exposes inherited read, write, update, and delete operations over these records. DAO initialization also creates and migrates the sys_user table (L180–L215); this is user-account management rather than storage of call content, fraud assessments, or analysis reports, and the manifest declares no such capability.

Content

No source excerpt is available for this finding.

ai_chat documents invoking an analysis agent but never invokes one or returns an analysis result.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The docstring at L25–L35 promises an openclaw agent invocation through subprocess and an analysis result or session ID. However, both the command arguments and subprocess invocation are commented out (L48–L66); the placeholder dictionary at L68 causes an AttributeError at L70, which is caught at L81–L82, leaving the method to return None. This contradicts the documented analysis behavior and could leave callers without the expected fraud assessment.

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

The generic open helper uses mode 'w', which immediately erases an existing file's contents. There is no docstring, explanatory comment, confirmation, or user-facing message disclosing this behavior; exception tracing does not warn about successful truncation.

Content

No source excerpt is available for this finding.

The request helper silently registers remote user accounts, extending the skill beyond call-risk analysis.

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

An ordinary HTTP request can trigger a separate phoneLogin request with silent registration enabled when credentials are missing. The helper exposes no explicit registration-consent gate, making remote account creation an unexpected side effect of call analysis rather than a user-approved account operation.

Content

No source excerpt is available for this finding.

The HTTP helper silently submits user identity data for automatic remote registration.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The registration payload sends the selected identity as both openId and mobile without a visible consent check. The caller can select an API secret as that identity, so this may also copy credential material into account-profile fields rather than keeping it confined to authentication headers.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This POST is the transmission sink for the automatic registration flow, sending identity data to the configured health-service endpoint without a visible approval step. External requests are not inherently unsafe, but this particular request performs undisclosed registration and can include an API secret repurposed as identity; the supplied 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 directories and files without disclosing the filesystem changes.

Low
Category
Output Handling
Confidence
92% confidence
Finding

At L017–L020, YamlUtil.load creates parent directories and writes a YAML file when the requested configuration is missing, without a comment, docstring, log, or confirmation explaining this side effect. BaseEnum.init_subclass calls this loader during class creation at L053 and L058, so merely importing the module can create configuration files.

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