Security audit

FigJam Storymap LLM

Security checks across malware telemetry and agentic risk

Overview

This skill appears safe to install; it reads a user-selected FigJam board and converts it to Markdown or JSON, with normal token and board-content privacy cautions.

Install only if you are comfortable letting the agent or parser read the selected FigJam board. Use a minimally scoped Figma token where possible, keep it in an environment variable or secret store, do not paste it into shared files or screenshots, and avoid running this on confidential boards unless your organization permits it.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 94% confidence
Finding: The skill instructs use of a Figma REST API token, reading saved JSON files, and making network requests, but it does not declare those capabilities or set user expectations about credential and data access. This creates a real security transparency issue: an agent could access environment secrets and transmit board contents externally without an explicit permission boundary, increasing the risk of unintended secret use or data exfiltration.

Missing User Warnings

Low

Confidence: 89% confidence
Finding: The skill asks for a FIGMA_TOKEN and describes pulling board data from the Figma REST API, but it provides no warning about credential handling, data transmission, or the sensitivity of workshop content. Even if the workflow is legitimate, users may unknowingly expose proprietary roadmap, product, or customer information to an external service without informed consent.

Missing User Warnings

Low

Confidence: 82% confidence
Finding: The document instructs users to supply a personal Figma access token for API use but does not include any handling guidance, such as storing it in environment variables, avoiding commits/logging, or using least-privilege and rotation practices. This is not credential theft by itself, but it increases the chance that users expose a sensitive token in shell history, screenshots, shared docs, or source control.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.secret_argv_exposure

Instructions pass high-value credentials through process argv.

Critical

Code: suspicious.secret_argv_exposure
Location: references/figjam-executive-summary.md:50

Instructions pass high-value credentials through process argv.

Critical

Code: suspicious.secret_argv_exposure
Location: references/figjam-template-spec.md:467

Instructions pass high-value credentials through process argv.

Critical

Code: suspicious.secret_argv_exposure
Location: SKILL.md:67