Anime Image Generator

• Outcome: Review
• Latest audit: May 28, 2026 · 7:38 AM UTC
• Version: 2026.3.23

Overview

This looks like a real WeryAI anime image generator, but it needs review because some setup and upload behavior is more silent or broader than the safety text suggests.

Install only if you are comfortable sending prompts and any referenced images to WeryAI. Prefer an environment variable or a carefully gitignored local secret file for IMAGE_GEN_API_KEY, review any request to install runtimes or packages, and avoid passing private local images as --ref unless you intend to upload them.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (8)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The document instructs the agent to run a 'silent' readiness pass before any user-facing warning, and that pass may auto-bootstrap local dependencies and inspect local environment state. Even if later installation requires approval, executing setup-related checks and possible changes without prior consent violates least surprise and can lead to unauthorized local actions in the user's workspace.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: This section directs the agent to persist secrets and configuration files on the user's behalf, including writing `.image-skills/image-generation/.env`, without an upfront warning that local files will be modified. Storing secrets automatically is sensitive because it changes the local security posture, may create plaintext secret files, and may surprise users who did not explicitly approve file creation or persistence.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill instructs the agent to initialize the workspace from a starter registry and immediately write `.image-skills/image-generation/EXTEND.md` with 'silent, no user involvement.' Automatic creation of workspace configuration without consent is a true vulnerability because it modifies project state and may affect future agent behavior in ways the user did not knowingly approve.

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The script can persist IMAGE_GEN_API_KEY into a local .env file on disk, which increases the risk of credential exposure through source control, backups, permissive filesystem access, or later tooling that reads project files. Although this appears to be a convenience feature rather than credential theft, writing secrets to project-local files is still a real security weakness if users do not understand the storage implications.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The instructions explicitly direct the agent to persist `IMAGE_GEN_API_KEY` to a local `.env` file, but they do not require user-visible disclosure of the risks of storing secrets on disk, such as accidental commit, local compromise, or leakage through backups and tooling. In an agentic setup flow, silently preferring persistent storage increases the chance that credentials are written in a way the user did not fully understand or intend.

Missing User Warnings

Low

• Confidence: 85% confidence
• Finding: The setup flow tells the agent to initialize configuration files silently and write `.image-skills/image-generation/EXTEND.md` before user involvement. While this is not directly a secret-handling flaw, unattended file creation/modification by an agent can violate user expectations, alter repository state, and in some environments create an opportunity for config abuse or persistence without clear approval.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: In image-to-image mode, local reference images are read from disk and converted to base64 data URLs before being sent to the remote WeryAI API. That is an intentional feature, but there is no explicit user-facing warning or consent checkpoint at the transmission point, so users may unknowingly upload sensitive local files if a prompt or batch file references them.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: This function sends user-supplied prompt data and generation parameters to a remote API endpoint without any disclosure, consent check, or indication in the code that the user is informed their content leaves the local agent boundary. In an image-generation skill, prompts may contain sensitive personal, proprietary, or policy-relevant content, so silent transmission to a third-party service creates a real privacy and data-handling risk even if the behavior is functionally expected.

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access, suspicious.potential_exfiltration

Shell command execution detected (child_process).

Critical

• Code: suspicious.dangerous_exec
• Location: scripts/bootstrap.mjs:86

Shell command execution detected (child_process).

Critical

• Code: suspicious.dangerous_exec
• Location: scripts/doctor.mjs:56

Shell command execution detected (child_process).

Critical

• Code: suspicious.dangerous_exec
• Location: scripts/smoke-check.mjs:18

Shell command execution detected (child_process).

Critical

• Code: suspicious.dangerous_exec
• Location: scripts/vendor/shared-image-generation/scripts/bootstrap.mjs:86

Shell command execution detected (child_process).

Critical

• Code: suspicious.dangerous_exec
• Location: scripts/vendor/shared-image-generation/scripts/doctor.mjs:56

Shell command execution detected (child_process).

Critical

• Code: suspicious.dangerous_exec
• Location: scripts/vendor/shared-image-generation/scripts/smoke-check.mjs:18

Shell command execution detected (child_process).

Critical

• Code: suspicious.dangerous_exec
• Location: scripts/vendor/weryai-image/discover-models.mjs:9

Shell command execution detected (child_process).

Critical

• Code: suspicious.dangerous_exec
• Location: scripts/vendor/weryai-image/doctor.mjs:9

Shell command execution detected (child_process).

Critical

• Code: suspicious.dangerous_exec
• Location: scripts/vendor/weryai-image/main.ts:14

Shell command execution detected (child_process).

Critical

• Code: suspicious.dangerous_exec
• Location: scripts/vendor/weryai-image/recommend-model.mjs:9

Shell command execution detected (child_process).

Critical

• Code: suspicious.dangerous_exec
• Location: scripts/vendor/weryai-image/run-generate.mjs:23

Shell command execution detected (child_process).

Critical

• Code: suspicious.dangerous_exec
• Location: scripts/vendor/weryai-image/setup.mjs:9

Environment variable access combined with network send.

Critical

• Code: suspicious.env_credential_access
• Location: scripts/main.ts:47

Environment variable access combined with network send.

Critical

• Code: suspicious.env_credential_access
• Location: scripts/vendor/shared-image-generation/scripts/main.ts:51

File read combined with network send (possible exfiltration).

Warn

• Code: suspicious.potential_exfiltration
• Location: scripts/main.ts:6

File read combined with network send (possible exfiltration).

Warn

• Code: suspicious.potential_exfiltration
• Location: scripts/vendor/shared-image-generation/scripts/main.ts:6