dubwerk/skill-scan
Security scanner for agent skills — detect prompt injection, malicious code, and data exfiltration
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| path | Path to the skill directory to scan (local) | no | . |
| repo | GitHub repository to scan (owner/repo or owner/repo@ref) | no | "" |
| fail-on | Exit with code 2 if any finding at or above this severity (critical, high, medium, low, info) | no | "" |
| format | Output format: text, json, or sarif | no | text |
| config | Path to skill-scan config file | no | "" |
Outputs
no outputs