ClawHub
Back to skill

Security audit

Alibabacloud Docmind Parse

Security checks for vulnerabilities and agentic risk

Overview

This document-parsing skill is mostly coherent, but it can upload sensitive documents over plaintext HTTP by default and accepts an unrestricted endpoint from the environment.

Review before installing. Use this only for documents you are allowed to send to Alibaba Cloud or another configured endpoint, avoid sensitive files unless policy permits it, and set an HTTPS endpoint explicitly. Treat DOCMIND_V2_ENDPOINT and SKILL_SESSION_ID as privacy-relevant configuration, and be aware that --output-file may overwrite an existing file.

A.I.G

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 (2)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/docmind_parse.py:25
Finding

Document Contents Are Transmitted over Plaintext HTTP by Default

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/docmind_parse.py:18
Finding

Unrestricted Configurable Endpoint Can Receive Documents and Session Identifiers

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (10)

Tainted flow: 'SKILL_USER_AGENT' from os.environ.get (line 18, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/docmind_parse.py (reported line 83)May include surrounding context.

python
url = f"{self.endpoint}/skill/submit"
        try:
            resp = requests.post(url, json=payload, timeout=30,
                                 headers={"User-Agent": SKILL_USER_AGENT})
        except requests.ConnectionError as e:
            raise RuntimeError(

Tainted flow: 'SKILL_USER_AGENT' from os.environ.get (line 18, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/docmind_parse.py (reported line 114)May include surrounding context.

python
url = f"{self.endpoint}/skill/submit"
        try:
            resp = requests.post(url, json=payload, timeout=30,
                                 headers={"User-Agent": SKILL_USER_AGENT})
        except requests.ConnectionError as e:
            raise RuntimeError(

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill does not prominently warn that local files, document contents, and URLs may be uploaded or transmitted to external Alibaba Cloud endpoints for processing. Users may provide sensitive internal documents without informed consent, leading to confidentiality, compliance, or data residency issues.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill can access environment variables, write files, and make outbound network requests, but it does not declare any explicit tool scope or permission boundaries. This weakens reviewability and enforcement, increasing the risk of unintended data access or exfiltration when the skill is invoked.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases include broad terms like document parsing and file parsing use cases, which can cause the skill to activate in situations beyond clear user intent. Because this skill transmits user-supplied files or URLs to external Alibaba Cloud services, over-broad activation raises the chance of accidental disclosure of sensitive documents.

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 · scripts/docmind_parse.py (reported line 83)May include surrounding context.

python
url = f"{self.endpoint}/skill/submit"
        try:
            resp = requests.post(url, json=payload, timeout=30,
                                 headers={"User-Agent": SKILL_USER_AGENT})
        except requests.ConnectionError as e:
            raise RuntimeError(

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 · scripts/docmind_parse.py (reported line 114)May include surrounding context.

python
url = f"{self.endpoint}/skill/submit"
        try:
            resp = requests.post(url, json=payload, timeout=30,
                                 headers={"User-Agent": SKILL_USER_AGENT})
        except requests.ConnectionError as e:
            raise RuntimeError(

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

When given a local file, the tool base64-encodes the document and uploads its contents to a remote DocMind V2 service, but the CLI does not provide an explicit warning or confirmation that local data is leaving the machine. In a document-processing skill, users may supply sensitive files, so silent remote upload creates a real privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This is a markdown file, so SQP-2 applies to omitted warnings about behaviors affecting privacy or system integrity. The credential configuration section lists AccessKey environment variables, local credential files, and instance metadata sources, but provides no explicit user warning that these are sensitive credentials that must be protected and should not be logged, shared, or hard-coded.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The script writes parsing output to the path supplied by --output-file, but there is no prior confirmation prompt or advance warning that an existing file may be overwritten. The success message appears only after the write, so it does not function as disclosure before the file-modifying operation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.