v1.0.0

WebChat Image Support

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 8:39 AM.

Analysis

This instruction-only skill coherently adds image understanding for user-sent images, with no code, install steps, credentials, or hidden behavior shown.

GuidanceThis appears safe to install as an instruction-only image-support skill. Before using it, make sure the configured vision model and chat channel are ones you trust, especially if users may upload private screenshots, documents, faces, or other sensitive images.

Findings (1)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication

SeverityInfoConfidenceHighStatusNote

SKILL.md

| Model supports images | Direct image input to model | ... | Model no images | Use media understanding pipeline |

This shows that user-sent images may be passed to a configured vision model or fallback media pipeline. That is central to the skill's purpose, but it is still a data-flow users should notice.

User impactPhotos or screenshots sent to the agent may be analyzed by the configured vision model or media processing pipeline, which could involve sensitive image content.

RecommendationUse trusted chat channels and model providers, and avoid sending sensitive images unless you are comfortable with the configured provider and OpenClaw media-processing settings.