Visual Content Desc
v1.0.0Generates detailed text descriptions of medical images and charts for.
⭐ 0· 34·0 current·0 all-time
byAIpoch@aipoch-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description claim 'generates detailed text descriptions of medical images and charts' which aligns with the package's purpose, but the actual implementation is a very small template-based generator that requires the caller to provide 'key_features'. The skill does not perform any image analysis or chart parsing itself; it formats provided inputs into text. This is coherent but the advertised capability is somewhat overstated compared with what the code actually does.
Instruction Scope
SKILL.md directs the agent to validate inputs and run the packaged script (scripts/main.py). It does not instruct reading unrelated files, contacting external endpoints, or accessing credentials. The README includes a security checklist and explicitly notes no external API calls and file path validation requirements; the packaged script itself reads no files and makes no network calls.
Install Mechanism
No install spec is provided (instruction-only with a small included script). No downloads or package installs are requested, so nothing is written to disk beyond the provided script when run. This is low risk from an install perspective.
Credentials
The skill declares no required environment variables, credentials, or config paths. The code and SKILL.md do not reference secrets or external service tokens, so requested access is proportionate to the stated purpose.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system-wide settings, and has no install-time hooks. Autonomous invocation (disable-model-invocation=false) is the platform default and not a concern by itself; combined with the minimal footprint here it does not create elevated persistence or privilege.
Assessment
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.Like a lobster shell, security has layers — review code before you run it.
latestvk979x89jyyf1tw8t0mck5g2p9d841nvf
License
MIT-0
Free to use, modify, and redistribute. No attribution required.