ClawHub
Back to skill

Security audit

Figma

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Figma integration through MorphixAI, with expected access to Figma data and comment actions but no evidence of hidden execution, persistence, or exfiltration in the reviewed artifact.

Install only if you are comfortable linking Figma through MorphixAI and granting the permissions available to that linked account. Keep MORPHIXAI_API_KEY out of source control and logs, and require clear confirmation before posting or deleting Figma comments, especially in shared or business workspaces.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:17
Finding
Unpinned Third-Party Plugin Handles Sensitive Figma Operations## Vulnerability Details **File Location**: `SKILL.md`, lines 17–20 **Vulnerability Type**: Unpinned third-party dependency and external account intermediary **Risk Level**: Medium ```text 1. **安装插件**: `openclaw plugins install openclaw-morphixai` 2. **获取 API Key**: 访问 [morphix.app/api-keys](https://morphix.app/api-keys) 生成 `mk_xxxxxx` 密钥 3. **配置环境变量**: `export MORPHIXAI_API_KEY="mk_your_key_here"` 4. **链接账号**: 访问 [morphix.app/connections](https://morphix.app/connections) 链接 Figma 账号，或通过 `mx_link` 工具链接（app: `figma`） ``` ### Technical Analysis The Skill directs users to install `openclaw-morphixai` without specifying an immutable version, package digest, signature, or other integrity constraint. It then requires a MorphixAI API key and directs the user to link a Figma account through the same third-party service. Because the audited project contains only `SKILL.md` and does not include the plugin implementation, its handling of credentials, authorization tokens, Figma content, and write operations cannot be independently verified from this artifact. An unpinned package can also change after the Skill has been reviewed, allowing a compromised publisher account or distribution channel to deliver behavior different from the reviewed documentation. The documentation transparently identifies MorphixAI as the intermediary; therefore, the audit does not establish hidden exfiltration or prove that the current plugin is malicious. The vulnerability is the mutable, externally supplied dependency being trusted with sensitive integration capabilities without reproducible versioning or integrity verification. ### Attack Path 1. An attacker compromises the plugin publisher, package distribution channel, or a mutable release associated with `openclaw-morphixai`. 2. A user follows the Skill instructions and installs the plugin by name without an immutable version or verified digest. 3. The user configures a valid `MORPHIXAI_API_KEY` and l ...[truncated 917 chars]
Remediation
## Remediation Suggestions 1. Pin `openclaw-morphixai` to a reviewed, immutable version rather than installing an unconstrained latest release. 2. Publish and verify a cryptographic digest or trusted signature for the exact plugin artifact. 3. Provide auditable plugin source code and reproducible build instructions so credential and data handling can be reviewed. 4. Document the precise Figma authorization scopes, MorphixAI data flow, retention policy, subprocess behavior, and third-party sharing policy. 5. Request least-privilege, read-only Figma permissions by default. Enable comment creation or deletion only when explicitly required. 6. Require explicit user confirmation immediately before write or destructive operations, particularly comment deletion. 7. Use short-lived, revocable credentials where supported, rotate integration keys regularly, and avoid exposing keys in logs or generated output. 8. Add dependency monitoring and an incident-response process for revoking MorphixAI keys and linked Figma authorization if the plugin or distribution channel is compromised.

SkillSpector

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 (3)

Missing User Warnings

Medium
Confidence
82% confidence
Finding
The file tells users to generate a MorphixAI API key and place it in `MORPHIXAI_API_KEY`, but provides no caution about treating the key as a secret, avoiding commits/history leaks, or limiting exposure. Since markdown files should warn about behaviours affecting privacy or system integrity, credential handling warrants a user-facing warning.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
This markdown file documents a destructive operation (`delete_comment`) that can permanently remove collaboration data, but it does not include any caution, confirmation note, or user warning near the example or in the precautions section. Under the markdown-specific warning rule, behaviours affecting user data should be disclosed clearly.

Natural-Language Policy Violations

Low
Confidence
94% confidence
Finding
The description and all usage instructions are written in Chinese, with no indication that another language is available or that the language choice is intentional and documented. The policy requires avoiding forced language/locale constraints unless users are given a choice or the constraint is justified.

Static analysis

No suspicious patterns detected.