T08 · Insecure Dependencies
Warning
- Location
SKILL.md:194- Finding
Unpinned Third-Party Dependencies Installed at Runtime
- Content
View full analysis
- Remediation
View remediation
Security audit
Universal Translator
Security checks for vulnerabilities and agentic risk
Overview
This is a document-translation helper with some documentation and dependency caveats, but no evidence of hidden, destructive, or credential-stealing behavior.
Install this only if you are comfortable with document contents being processed by the LLM configured in OpenClaw, especially for sensitive files. Treat PDF and HTML support as unimplemented or incomplete unless the publisher updates the skill, and prefer installing the listed Python packages in an isolated environment with pinned versions.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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)
Vulnerability Patterns
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The manifest description says the skill is a framework for translating Word, PDF, Excel, PowerPoint, HTML, Markdown, and TXT documents. However, the code only defines translation methods for Word, Excel, PowerPoint, and Markdown/text, and translate_folder never handles detected 'pdf' or 'html' formats, so the advertised behavior does not match the actual implementation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The warning about document content being sent to the configured LLM is written exclusively in Chinese, while the rest of the skill documentation is in English. This creates a language accessibility/policy issue because English-speaking users may miss an important privacy warning without being offered a language choice or equivalent English text.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The framework description says it provides boilerplate to read Word, Excel, PPT, and PDF files, while other parts of the document also advertise HTML support. But the code block has no PDF or HTML parser imports or translation methods, so the documentation actively overstates what the implementation does.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The example workflow for a PDF translation request implies that the skill can parse and rewrite PDF content. The code shown does not implement any PDF translation method or folder dispatch for PDF files, so the example contradicts the actual capabilities of the skill.
- Content
Scope Creep
Low
- Category
- Excessive Agency
- Confidence
- 70% confidence
- Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
- Content
text permit persons to whom the Software is furnished to do so. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 86% confidence
- Finding
The documentation explicitly states that only modern formats are supported and that .xls files must be converted to .xlsx first. In contrast, the code includes '.xls' in the supported Excel extensions, which contradicts the stated intent and may mislead an agent into attempting unsupported processing.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The notes section states that PDF and HTML are supported and recommends installing pymupdf and beautifulsoup4. The provided Python code imports neither library and contains no PDF or HTML translation functions, so the documentation contradicts the implementation.
- Content
Static analysis
No suspicious patterns detected.