Back to skill

Security audit

Cyberpunk Image Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill is a mostly disclosed WeryAI image-generation wrapper, but it has a material API-key exposure flaw and weak secret/runtime handling that should be reviewed before installation.

Install only if you are comfortable with a third-party WeryAI gateway wrapper that stores local config and may persist an API key. Use a restricted or disposable API key, avoid persisting it on shared machines, review generated download URLs and reference-image uploads, and prefer a locally installed trusted Bun runtime over the unpinned `npx -y bun` path.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (3)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/main.ts:186
Finding

API Key Forwarded to Arbitrary Gateway-Provided Image URLs

Content
View full analysis
``` if the server returns HTTP 401 or 403. It also proceeds to an authenticated attempt after an unauthenticated network exception. The URL is taken from `detail.images`, which i ...[truncated 2027 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/setup.mjs:126
Finding

Persisted API Key File Is Not Given Restrictive Permissions

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
scripts/package.json:6
Finding

Unpinned Bun Package Is Retrieved and Executed Through npx

Content
View full analysis
Remediation
View remediation
`. 4. Verify package integrity and provenance before execution. 5. Require explicit user approval before downloading or executing a runtime package. 6. Use a lockfile where npm dependencies are involved and review all resolved transitive dependencies. 7. Consider distributing a verified runtime binary with checksum or signature validation. 8. Ensure sensitive environment variables are not inherited by installer or package-resolution subprocesses unless strictly required. 9. Apply the same controls to generation, smoke-check, and test commands. ]]>
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (107)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill markets itself as cyberpunk-focused, but also accepts arbitrary prompts, arbitrary models, and generic image-to-image workflows. In context, that mismatch is meaningful because a narrowly branded creative skill may receive less scrutiny than a general remote media-processing gateway with file and network capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill markets itself as cyberpunk-focused, but also accepts arbitrary prompts, arbitrary models, and generic image-to-image workflows. In context, that mismatch is meaningful because a narrowly branded creative skill may receive less scrutiny than a general remote media-processing gateway with file and network capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill markets itself as cyberpunk-focused, but also accepts arbitrary prompts, arbitrary models, and generic image-to-image workflows. In context, that mismatch is meaningful because a narrowly branded creative skill may receive less scrutiny than a general remote media-processing gateway with file and network capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill markets itself as cyberpunk-focused, but also accepts arbitrary prompts, arbitrary models, and generic image-to-image workflows. In context, that mismatch is meaningful because a narrowly branded creative skill may receive less scrutiny than a general remote media-processing gateway with file and network capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill markets itself as cyberpunk-focused, but also accepts arbitrary prompts, arbitrary models, and generic image-to-image workflows. In context, that mismatch is meaningful because a narrowly branded creative skill may receive less scrutiny than a general remote media-processing gateway with file and network capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill markets itself as cyberpunk-focused, but also accepts arbitrary prompts, arbitrary models, and generic image-to-image workflows. In context, that mismatch is meaningful because a narrowly branded creative skill may receive less scrutiny than a general remote media-processing gateway with file and network capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill markets itself as cyberpunk-focused, but also accepts arbitrary prompts, arbitrary models, and generic image-to-image workflows. In context, that mismatch is meaningful because a narrowly branded creative skill may receive less scrutiny than a general remote media-processing gateway with file and network capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill markets itself as cyberpunk-focused, but also accepts arbitrary prompts, arbitrary models, and generic image-to-image workflows. In context, that mismatch is meaningful because a narrowly branded creative skill may receive less scrutiny than a general remote media-processing gateway with file and network capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The skill markets itself as cyberpunk-focused, but also accepts arbitrary prompts, arbitrary models, and generic image-to-image workflows. In context, that mismatch is meaningful because a narrowly branded creative skill may receive less scrutiny than a general remote media-processing gateway with file and network capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill markets itself as cyberpunk-focused, but also accepts arbitrary prompts, arbitrary models, and generic image-to-image workflows. In context, that mismatch is meaningful because a narrowly branded creative skill may receive less scrutiny than a general remote media-processing gateway with file and network capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The skill markets itself as cyberpunk-focused, but also accepts arbitrary prompts, arbitrary models, and generic image-to-image workflows. In context, that mismatch is meaningful because a narrowly branded creative skill may receive less scrutiny than a general remote media-processing gateway with file and network capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill markets itself as cyberpunk-focused, but also accepts arbitrary prompts, arbitrary models, and generic image-to-image workflows. In context, that mismatch is meaningful because a narrowly branded creative skill may receive less scrutiny than a general remote media-processing gateway with file and network capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The skill markets itself as cyberpunk-focused, but also accepts arbitrary prompts, arbitrary models, and generic image-to-image workflows. In context, that mismatch is meaningful because a narrowly branded creative skill may receive less scrutiny than a general remote media-processing gateway with file and network capabilities.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

md
| Base URL | `https://api.weryai.com` (hard-coded in `scripts/main.ts`) |

Credential Access

High
Category
Privilege Escalation
Confidence
84% confidence
Finding

The skill is designed to obtain, persist, and use an API key from environment files under project or home directories. Even though it says not to print the key, encouraging the agent to manage and store credentials locally enlarges the secret-handling surface and raises the risk of accidental disclosure, misuse, or insecure storage.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

md
3. **If `IMAGE_GEN_API_KEY` is missing**, ask the user for permission to configure it now
4. Only after readiness and API key are resolved, continue to model selection / prompt clarification / generation

**Access token**: only use **`IMAGE_GEN_API_KEY`**. It may also live in `.image-skills/cyberpunk-image-generator/.env` as `IMAGE_GEN_API_KEY=...`. After the user approves, the agent may persist it there by running `npm run setup -- --project . --workflow <workflow> --persist-api-key` when the key is already in env, or by writing the file locally on the user's behalf instead of asking the user to edit files manually.

**First-use readiness check**: before the first generation run in a new OpenClaw or local instance, the agent must run:

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · scripts/main.ts (reported line 596)May include surrounding context.

ts
}

function applyStylePreset(prompt: string, style: StylePreset | null | undefined): string {
  if (!style) return prompt;
  return `${prompt.trim()}\n\nStyle preset (${style}): ${STYLE_PRESETS[style]}.`;
}

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · scripts/vendor/shared-image-generation/scripts/main.ts (reported line 602)May include surrounding context.

ts
}

function applyStylePreset(prompt: string, style: StylePreset | null | undefined): string {
  if (!style) return prompt;
  return `${prompt.trim()}\n\nStyle preset (${style}): ${STYLE_PRESETS[style]}.`;
}

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The code reads IMAGE_GEN_API_KEY from process.env or CLI arguments and writes it into a .env file, directly handling and persisting credentials. This is dangerous because secrets passed on the command line may be exposed via shell history or process inspection, and secrets written to disk can later be leaked through source control, logs, or unintended file access.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · scripts/doctor.mjs (reported line 90)May include surrounding context.

js
const projectSkillDir = path.join(projectRoot, ".image-skills", skillNamespace);
  const homeSkillDir = homeRoot ? path.join(homeRoot, ".image-skills", skillNamespace) : null;

  const projectEnvPath = path.join(projectRoot, ".image-skills", skillNamespace, ".env");
  const projectEnvFile = pathExists(projectEnvPath);
  let apiKeyInProjectEnv = false;
  if (projectEnvFile) {

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · scripts/main.ts (reported line 397)May include surrounding context.

ts
const projectSkillDir = path.join(projectRoot, ".image-skills", skillNamespace);
  const homeSkillDir = homeRoot ? path.join(homeRoot, ".image-skills", skillNamespace) : null;

  const projectEnvPath = path.join(projectRoot, ".image-skills", skillNamespace, ".env");
  const projectEnvFile = pathExists(projectEnvPath);
  let apiKeyInProjectEnv = false;
  if (projectEnvFile) {

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · scripts/main.ts (reported line 470)May include surrounding context.

ts
const projectSkillDir = path.join(projectRoot, ".image-skills", skillNamespace);
  const homeSkillDir = homeRoot ? path.join(homeRoot, ".image-skills", skillNamespace) : null;

  const projectEnvPath = path.join(projectRoot, ".image-skills", skillNamespace, ".env");
  const projectEnvFile = pathExists(projectEnvPath);
  let apiKeyInProjectEnv = false;
  if (projectEnvFile) {

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · scripts/main.ts (reported line 471)May include surrounding context.

ts
const projectSkillDir = path.join(projectRoot, ".image-skills", skillNamespace);
  const homeSkillDir = homeRoot ? path.join(homeRoot, ".image-skills", skillNamespace) : null;

  const projectEnvPath = path.join(projectRoot, ".image-skills", skillNamespace, ".env");
  const projectEnvFile = pathExists(projectEnvPath);
  let apiKeyInProjectEnv = false;
  if (projectEnvFile) {

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · scripts/vendor/shared-image-generation/scripts/doctor.mjs (reported line 90)May include surrounding context.

js
const projectSkillDir = path.join(projectRoot, ".image-skills", skillNamespace);
  const homeSkillDir = homeRoot ? path.join(homeRoot, ".image-skills", skillNamespace) : null;

  const projectEnvPath = path.join(projectRoot, ".image-skills", skillNamespace, ".env");
  const projectEnvFile = pathExists(projectEnvPath);
  let apiKeyInProjectEnv = false;
  if (projectEnvFile) {

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · scripts/vendor/shared-image-generation/scripts/main.ts (reported line 403)May include surrounding context.

ts
const projectSkillDir = path.join(projectRoot, ".image-skills", skillNamespace);
  const homeSkillDir = homeRoot ? path.join(homeRoot, ".image-skills", skillNamespace) : null;

  const projectEnvPath = path.join(projectRoot, ".image-skills", skillNamespace, ".env");
  const projectEnvFile = pathExists(projectEnvPath);
  let apiKeyInProjectEnv = false;
  if (projectEnvFile) {

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · scripts/vendor/shared-image-generation/scripts/main.ts (reported line 476)May include surrounding context.

ts
const projectSkillDir = path.join(projectRoot, ".image-skills", skillNamespace);
  const homeSkillDir = homeRoot ? path.join(homeRoot, ".image-skills", skillNamespace) : null;

  const projectEnvPath = path.join(projectRoot, ".image-skills", skillNamespace, ".env");
  const projectEnvFile = pathExists(projectEnvPath);
  let apiKeyInProjectEnv = false;
  if (projectEnvFile) {