Api Gateway

Security checks across malware telemetry and agentic risk

Overview

This skill is a broad API gateway that can send data and use service tokens without clearly defined safety boundaries.

Install only if you can tightly control which APIs and credentials the skill may use. Prefer read-only, least-privilege tokens, avoid query-string secrets and broad workspace tokens, require explicit approval for POST or other write operations, and disable proactive or multi-agent use unless you have clear permission, logging, cache cleanup, and redaction rules.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill is explicitly designed to connect to arbitrary external REST/GraphQL APIs, send requests, and expose logs, but it does not describe any safeguards around data classification, credential redaction, destination allowlisting, or user-consent boundaries. In an agent context, this can enable sensitive prompts, user data, API tokens, or internal metadata to be transmitted to untrusted endpoints or revealed through logs.

External Transmission

Medium
Category
Data Exfiltration
Content
```
# Agregar nueva API
api add weather
  --base:https://api.openweathermap.org/data/2.5
  --auth:query:appid:$WEATHER_API_KEY

# Agregar endpoint
Confidence
88% confidence
Finding
https://api.openweathermap.org/

External Transmission

Medium
Category
Data Exfiltration
Content
api call weather current --q:"Mexico City" --units:metric

# Llamada directa con URL
api get https://api.example.com/data

# POST con body
api post https://api.example.com/create --body:'{"name":"test"}'
Confidence
90% confidence
Finding
https://api.example.com/

External Transmission

Medium
Category
Data Exfiltration
Content
api get https://api.example.com/data

# POST con body
api post https://api.example.com/create --body:'{"name":"test"}'
```

### Gestión
Confidence
91% confidence
Finding
https://api.example.com/

External Transmission

Medium
Category
Data Exfiltration
Content
```yaml
# apis/weather.yaml
name: weather
base_url: https://api.openweathermap.org/data/2.5
auth:
  type: query
  param: appid
Confidence
84% confidence
Finding
https://api.openweathermap.org/

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal