qwed-ai/QWED Protocol Verification
Verify LLM outputs with Z3/SymPy. Scan secrets, code, and shell scripts. SARIF output for GitHub Security.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| api_key | QWED API Key (Optional for local mode) | no | — |
| action | Action type: verify, scan-secrets, scan-code, verify-shell | no | verify |
| provider | LLM provider (e.g. openai, anthropic) | no | — |
| model | Model name | no | — |
| mask_pii | Mask PII in inputs/outputs | no | false |
| query | The user query (e.g. "Derivative of x^2") - used with action=verify | no | — |
| llm_output | The LLM output to verify - used with action=verify | no | — |
| engine | Verification Engine: math, logic, code, sql, shell | no | math |
| paths | Glob patterns for files to scan (e.g. "**/*.py,**/*.env") | no | . |
| output_format | Output format: text, json, sarif | no | text |
| fail_on_findings | Fail the action if security issues are found | no | true |
Outputs
| name | description |
|---|---|
| verified | True if verification passed or no issues found |
| explanation | Detailed proof or error explanation |
| findings_count | Number of security issues found (for scan modes) |
| badge_url | URL for QWED verified badge |
| sarif_file | Path to SARIF output file (if output_format=sarif) |