momenbasel/VulnHawk Security Scan
AI-powered code security scanner that finds vulnerabilities Semgrep and CodeQL miss
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| target | Path to scan (file or directory) | no | . |
| backend | LLM backend (claude, claude-code, openai, codex, ollama) | no | claude |
| model | Specific model name | no | — |
| mode | Scan mode (full, auth, injection, secrets, config, crypto) | no | full |
| severity | Minimum severity to report (critical, high, medium, low, info) | no | medium |
| api-key | API key for the LLM backend. Not required for claude-code backend. | no | "" |
| claude-code-oauth-token | OAuth token for Claude Code CLI backend (free for Claude Code subscribers) | no | "" |
| sarif-input | Path to SARIF file from other SAST tools (Semgrep, CodeQL) to enrich VulnHawk analysis | no | "" |
| fail-on-findings | Fail the workflow if critical/high findings are detected | no | true |
| sarif-file | Path to write SARIF output for GitHub Code Scanning | no | vulnhawk-results.sarif |
Outputs
| name | description |
|---|---|
| findings-count | Total number of findings |
| critical-count | Number of critical findings |
| sarif-file | Path to SARIF results file |