ClawHub
Back to skill

Security audit

Gamma App API

Security checks across malware telemetry and agentic risk

Overview

This Gamma API skill mostly matches its stated purpose, but it needs Review because crafted prompt text can execute local Python before the Gamma API call.

Install only after the script is fixed to build JSON from arguments or stdin safely instead of interpolating text into Python source. Use a revocable Gamma API key, avoid sensitive prompts unless Gamma is approved for them, and only enable workspace or external sharing when you explicitly intend broader access.

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 (2)

Vague Triggers

Medium
Confidence
81% confidence
Finding
The trigger list includes very broad terms such as "gamma" and especially "slides," which can cause the skill to activate for unrelated user requests. Because this skill sends user-provided content to an external API and can generate/export artifacts, accidental invocation could leak sensitive prompt content or perform unintended third-party actions.

Missing User Warnings

Low
Confidence
95% confidence
Finding
The API reference shows a secret-bearing authentication header example (`X-API-KEY: sk-gamma-xxxxx`) without any accompanying warning that API keys are sensitive credentials and must not be hardcoded, logged, or exposed in client-side contexts. In a skill intended to integrate with an external API, this omission can normalize unsafe handling of secrets and increase the chance that users or implementers leak credentials in prompts, code, or shared artifacts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.