Security audit
Security checks across malware telemetry and agentic risk
This skill runs a local skill-search API and shows no evidence of stealing data or taking unsafe actions, though its registry results appear to come from a bundled static list rather than live registry searches.
Before installing, understand that recommendations may be stale or sample-like because the registry data is bundled in the package. Do not put secrets or private data into search prompts, and verify any suggested skill on its actual registry page before installing it.
## Search across all registries
```bash
curl -s -X POST http://localhost:8016/v1/search \
-H "Content-Type: application/json" \
-d '{"query": "security scanning"}' | jq
```## Get recommendations for a problem
```bash
curl -s -X POST http://localhost:8016/v1/recommend \
-H "Content-Type: application/json" \
-d '{"problem": "I need to validate data before passing it to another agent"}' | jq
```## Filter by registry
```bash
curl -s -X POST http://localhost:8016/v1/search \
-H "Content-Type: application/json" \
-d '{"query": "code review", "registries": ["clawhub"], "max_results": 5}' | jq
```65/65 vendors flagged this skill as clean.
No suspicious patterns detected.