Volc Image Gen

Use Volc Engine AI to generate, edit, batch produce, and create variations of images with customizable styles and sizes.

Things to check before installing/using this skill: 1) Confirm the registry metadata: the package clearly requires VOLC_API_KEY (and optionally VOLC_API_BASE/VOLC_IMAGE_MODEL) but the top-level listing claimed no env vars. Ask the publisher or marketplace to correct the listing if necessary. 2) Treat VOLC_API_KEY as sensitive: grant it only if you trust the Volc Engine service and the skill's author. The skill will send images (including local files you supply) to the external Volc API. 3) Be cautious with local file paths: the skill will read local images and upload them (Base64) to the remote API. Do not pass paths to sensitive files or directories you don't want transmitted. 4) Inspect SKILL.md for hidden characters (the pre-scan found unicode control characters). Prefer a clean copy and consider scanning files for invisible/control characters before running. 5) Run tests and initial usage in an isolated environment (container or VM) and with a limited/test API key to avoid accidental data leakage or unexpected costs. 6) If you need stronger assurance, request source provenance: a trustworthy repository URL, maintainer identity, and release signatures. The included GitHub link in docs should be verified manually. Overall: behavior is consistent with an image-generation skill, but the metadata mismatch and the control-character finding merit caution — treat this as suspicious until those issues are resolved.

Type: OpenClaw Skill Name: volc-image-gen Version: 1.0.0 The skill bundle contains a significant security vulnerability in 'src/utils.js' within the 'loadImage' function, which allows for arbitrary file reading from the host system. Because the function does not sanitize or restrict the file path provided in the 'image' parameter, an attacker or a manipulated agent could read sensitive files (e.g., /etc/passwd, ~/.ssh/id_rsa) and exfiltrate them as Base64 data to the configured API endpoint (defaulting to Volcengine). While this is presented as a feature for processing local images, the lack of path validation constitutes a high-risk vulnerability. No explicit evidence of intentional malice or hardcoded exfiltration targets was found.