inject-guard
shallowcom.obsmetrics.paygent/agents · Verify this server
Untrusted-content guardrail for agents: submit a blob of text you are about to feed to your own LLM (scraped web content, a tool result, another agent's message) and get a machine-enforceable verdict - is this a prompt-injection / jailbreak / data-exfiltration / tool-hijack attempt? Returns a risk level, the detected classes with spans, the unicode obfuscation it found (zero-width, bidi-override, tag-chars, homoglyphs), and a SANITIZED copy safe to feed onward. Hybrid: a deterministic, uninjectable pattern engine (authoritative) plus an LLM classifier that can only raise the risk, never clear a flag. Detection of known injection classes - not a proof of safety. [security; up to 15c/call]
1 trials · measured 8 days ago
inject-guard scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against com.obsmetrics.paygent/agents, measured 25 Aug 2026 under methodology v0.2.0. Every measured component scored 100.
Component breakdown
| Component | Weight | Value |
|---|---|---|
| Reliability | 35% | not applicable |
| Schema integrity | 25% | 100.0 |
| Failure behaviour | 15% | not applicable |
| Latency | 15% | not applicable |
| Concurrency | 10% | not applicable |
Tool details
- Transport
- remote
- Credential class
- self-provisionable
- Category
- Communication
- Input schema
- not declared
- Output schema
- not declared
- Side-effect classification
- unclassified
Score history
| Day | Score | Tier | Methodology |
|---|---|---|---|
| 2026-08-25 | 100.0 | shallow | v0.2.0 |
Probe evidence
| Probe | Outcomes |
|---|---|
| schema_integrity | pass: 1 |
Raw request/response logs are not archived yet — the outcome counts above are drawn directly from every recorded trial.
Embed this score
Available for every tool, scored or not — not a verification perk. Always links back to this page.
[](https://vouch.tools/tools/b7580927-d058-439e-ad26-13fb83de3326)