Compare · bake-off
bezoar vs Company A
Venture-backed OSS scanner. No published benchmark — so we ran one. 88.2% vs 12.8% detection. 0 vs 181 false positives. Fixture: 10/10 vs 0/10.
Same corpus · default configs
| Metric | bezoar | Company A |
|---|---|---|
| Detection (626 malicious) | 88.2% | 12.8% |
| Flagged, absolute | 552/626 | 80/626 |
| False positives (737 official) | 0 | 181 |
| False positives (180 MCP Registry) | 0 | 0 |
| Curated fixture | 10/10 | 0/10 |
Why the gap
- No prompt-injection class. Tool poisoning, shadow instructions, and “don't tell the user” are invisible unless a credential path or reverse-shell one-liner happens to match.
- False positives from a bare
ncatalternative — matches insidetruncateandconcatenatein vendor docs. - Offline regex mode, no API key, one scan per sample, no tuning. “Flagged” is any finding — their threshold, not ours. Corpus and JSON public.
Beyond the scanner
Company A is a scanner. bezoar is a control plane. Scope gap, not a bake-off.
| Capability | bezoar | Company A |
|---|---|---|
| Desktop guard — allow / ask / deny | macOS · Linux | scanner only |
| MCP gateway — scan · pin · rug-pull | stdio · HTTP | scanner only |
| Install quarantine + trust ledger | bezoar fetch | scanner only |
| Fleet inventory + finding lifecycle | self-hosted console | scanner only |
| CI ingest + notifications | bezoar ingest | scanner only |
| Policy history · diff · restore | yes | scanner only |
| Framework mappings on every rule | OWASP · ATLAS · ATT&CK · CWE | scanner only |