Back to skill

Security audit

figma

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this Figma-related skill suspicious because it uses unpinned package commands and has a reported Windows executable lookup weakness; some files were only partially analyzed.

Consider the suspicious verdict before installing. In particular, review the unpinned package commands and the Windows PATH finding. The scan is incomplete: only 1 of 3 components was fully scanned, and tool-misuse analysis of 2 scripts was partial, so the results do not establish that the skill is safe.

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
  • 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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (10)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 16)May include surrounding context.

md
## Access

`FIGMA_TOKEN` in the shell or the project `.env`. Check it exists before the first command; if not, tell the person how to make one and stop: figma.com → Settings → Security → Personal access tokens, read-only **File content** and **File metadata**, plus **Library content** for `tokens` on non-Enterprise plans. They set it themselves; never ask them to paste it into the chat.

| Error | Meaning |
| --- | --- |

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx hyperframes'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

Although this is a CLI invocation rather than an MCP server declaration, unversioned npx can fetch and execute a changing package when no suitable local installation exists. A compromised release could execute with the agent's filesystem and environment access, including credentials; even the startup telemetry command introduces this exposure.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx hyperframes'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The asset command uses an unversioned executable that npx may download rather than a reviewed, fixed dependency. A compromised package would run in the project context and could access the Figma token and local files, making the authenticated import workflow a consequential supply-chain exposure.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx hyperframes'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The tokens command leaves package selection unpinned, allowing npx to resolve a changing release when a local dependency is unavailable. Compromise of that release could expose authentication credentials and private design data under the agent's privileges.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx hyperframes'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The component import command can execute an unpinned package fetched by npx. A malicious or compromised release would inherit project write access and potentially Figma credentials, enabling data theft or modification of generated application code.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx hyperframes'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The completion beacon repeats the unpinned npx execution pattern, so it can resolve code outside a reproducible dependency installation. A compromised package could execute with the agent's privileges even though the requested operation is only an event submission.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx hyperframes'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The motion-start beacon invokes an unversioned package through npx, potentially downloading executable code merely to report usage. If the resolved release is compromised, it receives the agent process's access to project files and environment secrets.

Content

No source excerpt is available for this finding.

The comments promise to disable both implicit working-directory executable lookup and relative PATH entries, but the Windows branch leaves PATH unchanged.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The Windows branch sets NoDefaultCurrentDirectoryInExePath but does not remove relative or empty PATH entries, leaving a separate route for resolving executables from an attacker-influenced project directory. If a later name-based subprocess lookup honors those entries, an attacker-supplied executable can run with the agent's privileges despite the claimed hardening.

Content

No source excerpt is available for this finding.

The skill requires usage telemetry unrelated to importing or animating Figma designs.

Low
Category
Excessive Agency
Confidence
96% confidence
Finding

The startup instruction runs a usage beacon that sends the skill name with the CLI's usual telemetry, account-linked when signed in. Line L34 additionally requires phase-specific start and completion events. These reporting operations are not needed to retrieve Figma assets or construct video compositions and are not declared in the manifest's stated purpose, although the instructions disclose them and honor the telemetry opt-out.

Content

No source excerpt is available for this finding.