Dangerous exec
Critical
- Finding
- Shell command execution detected (child_process).
Image Generation
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The skill mostly matches its stated image-generation purpose and requests only the expected API key and Node toolchain, but there are instruction inconsistencies (local reference handling vs rejection) and convenience behaviors (auto-install, writing API key to disk) that could surprise users and deserve careful review before installing.
This skill is broadly coherent for a WeryAI gateway wrapper, but review these points before installing: - Confirm you trust the WeryAI gateway (https://api.weryai.com). The skill will send prompts and possibly reference images to that endpoint. - The only credential requested is IMAGE_GEN_API_KEY — use a dedicated, limited-scope key if possible. Prefer setting it in your environment rather than allowing the skill to persist it to disk. - The agent may propose to run npm install and other bundled scripts. Installing will execute third-party JavaScript (from package.json) in your environment; approve installs only when you are comfortable with that. - The SKILL.md contains an inconsistency about reference images: one place says local file paths and data: URLs are rejected, another says the CLI can encode local files as data:image;base64. Ask the maintainer (or inspect scripts) to confirm the actual behavior if you rely on local reference images. - The skill will initialize EXTEND.md and a default model (Nano Banana 2) in the workspace on first run unless you change that. If you don't want files created automatically, decline the initial write or run setup manually. If you want to proceed: (1) review scripts/setup.mjs and scripts/bootstrap.mjs in the bundle to see exactly what the agent will run when it asks to install or persist keys; (2) supply a dedicated API key and deny persistent storage if you prefer ephemeral usage; (3) approve installs only after inspecting package.json dependency lists.
Static analysis
Dangerous exec
Critical
- Finding
- Shell command execution detected (child_process).
Dangerous exec
Critical
- Finding
- Shell command execution detected (child_process).
Dangerous exec
Critical
- Finding
- Shell command execution detected (child_process).
Dangerous exec
Critical
- Finding
- Shell command execution detected (child_process).
Dangerous exec
Critical
- Finding
- Shell command execution detected (child_process).
Dangerous exec
Critical
- Finding
- Shell command execution detected (child_process).
Dangerous exec
Critical
- Finding
- Shell command execution detected (child_process).
Dangerous exec
Critical
- Finding
- Shell command execution detected (child_process).
Dangerous exec
Critical
- Finding
- Shell command execution detected (child_process).
Dangerous exec
Critical
- Finding
- Shell command execution detected (child_process).
Dangerous exec
Critical
- Finding
- Shell command execution detected (child_process).
Env credential access
Critical
- Finding
- Environment variable access combined with network send.
Env credential access
Critical
- Finding
- Environment variable access combined with network send.
Potential exfiltration
Warn
- Finding
- File read combined with network send (possible exfiltration).
Potential exfiltration
Warn
- Finding
- File read combined with network send (possible exfiltration).
VirusTotal
No VirusTotal findings
Risk analysis
No visible risk-analysis findings were reported for this release.