Visual Content Desc

Generates detailed text descriptions of medical images and charts for.

This skill appears safe from a security/configuration perspective — it runs a small local Python script that formats supplied 'image_type' and 'key_features' into description text. Before using it in production, note: (1) the script does not perform any image analysis — you must supply the visual features yourself, so the skill's advertising of 'detailed' descriptions is dependent on the input quality; (2) do not feed it PHI or sensitive images unless you have reviewed and approved handling policies, because outputs will reflect whatever you input; (3) run the quick checks recommended in SKILL.md (python -m py_compile scripts/main.py, run the script locally with test inputs) to confirm behavior in your environment; (4) if you need real image/chart parsing, expect to integrate additional vetted libraries and re-evaluate dependencies and permissions. If any additional files or install steps are later added to this skill, re-run a security review.

Type: OpenClaw Skill Name: visual-content-desc Version: 1.0.0 The skill is a straightforward utility for generating text descriptions and alt-text for medical images. The Python script (scripts/main.py) performs simple string formatting and JSON output without any external dependencies, network calls, or risky system executions. The instructions in SKILL.md are consistent with the stated functionality and do not contain any malicious directives or prompt injection attempts.