Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 3. Run `translate.mjs` for the uncertain passage (or the whole text).
Security audit
deepl-translate-node
Security checks for vulnerabilities and agentic risk
Overview
This is a coherent DeepL translation helper, but users should understand that translated text is sent to DeepL using their API key.
Install only if you are comfortable sending the text you translate to DeepL. Avoid pasting secrets, regulated data, confidential business material, or private client content unless you have approval. Keep DEEPL_API_KEY private, and only set DEEPL_API_HOST to DeepL's official Free or Pro API hosts.
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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Rogue AgentSelf-Modification, Session Persistence
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 93% confidence
- Finding
The skill invokes a Node helper that reads environment variables and makes outbound requests to the DeepL API, but the manifest does not declare an explicit tool scope such as permissions or allowed-tools. That weakens policy enforcement and user visibility, increasing the chance the skill is run with broader capabilities than intended.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The skill encourages sending arbitrary text to DeepL but does not prominently disclose that user content leaves the local environment and is transmitted to a third-party service. This can expose confidential, regulated, or proprietary text if users assume the translation is performed locally.
- Content
Session Persistence
Medium
- Category
- Rogue Agent
- Confidence
- 90% confidence
- Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
- Content
Set it once:
bash # macOS / Linux — add to ~/.bashrc or ~/.zshrc to persist export DEEPL_API_KEY="your-deepl-auth-key-here"
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
This skill sends user-provided text to DeepL over the network, which can expose sensitive, confidential, or regulated content to a third-party service if the caller is unaware of that data flow. In this context, the skill is explicitly a translation tool, so the behavior is expected, but the absence of an explicit privacy/disclosure warning still creates a real data-handling risk for users who may paste secrets, legal, medical, or internal text.
- Content
Static analysis
No suspicious patterns detected.