Security audit

translateflow-api

Security checks across malware telemetry and agentic risk

Overview

This translation skill is coherent but should be reviewed because it broadly routes user text, documents, and signup email addresses to an external translation service without clear consent or privacy boundaries.

Install only if you want an agent to use TranslateFlow's external API for translation tasks. Before using it, make sure the agent asks before sending your email, text, documents, URLs, or CMS content to the provider, and avoid legal, medical, confidential, or regulated material unless you have verified the provider's privacy and retention terms.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The skill description is packed with broad translation-related trigger phrases that can match many ordinary user requests, increasing the chance the skill activates when a user only wanted general conversational help. That can unnecessarily route user content to an external service and expand data exposure beyond user expectations.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The final guidance says to use the skill whenever users need translation or localization, but does not distinguish between simple in-model assistance and actions requiring external API calls. This ambiguity can cause unintended skill invocation and silent transfer of user data to a third-party service.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The skill instructs collecting the user's email address and sending it to an external API to create an account, but provides no privacy notice, consent step, or explanation of how the email will be used. This creates a privacy and compliance risk because personally identifiable information is transmitted to a third party without informed user approval.

Missing User Warnings

High

Confidence: 99% confidence
Finding: The skill repeatedly instructs sending user text and documents to external translation endpoints but never warns that potentially sensitive content will leave the local system and be processed by a third party. Because translation requests may include legal, medical, commercial, or personal documents, this omission materially increases confidentiality and compliance risk.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: SKILL.md:47