Multimodal Asset Tagger
PassAudited by ClawScan on May 1, 2026.
Overview
This skill appears benign: it provides asset-metadata guidance and a small local Python helper, with no credentials, network access, persistence, or exfiltration shown.
This skill is reasonable to use for drafting asset metadata. Before running the optional Python helper, review the short script and note that the package does not provide an external homepage or source repository for provenance.
Findings (2)
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.
You have less external context for who maintains the skill or where to verify updates.
The skill does not provide an upstream source or homepage, so users have less provenance context even though the included files are small and show no suspicious dependency or install behavior.
Source: unknown; Homepage: none
Review the included files before use and prefer installing from a trusted registry or source when available.
Using the helper means running code from the skill package on your machine.
The quick start asks the user to run a local Python helper. The provided script is simple and purpose-aligned, but local code execution is still behavior users should notice.
python scripts/optimize_asset.py --type image --description "dashboard showing metrics" --output optimized.md
Run the helper only after reviewing it; the included script shown here only parses arguments and prints alt text and a filename.