check_instruction
shallowco.fingersai/fingers · Verify this server
Is this CONTENT safe for an agent to ACT ON? Screens a message / tweet / DM / webpage / tool output an agent is about to treat as an instruction, for prompt-injection and social-engineering ('ignore previous instructions', 'send funds to', 'approve this', 'admin override', 'claim your airdrop' links). This is how autonomous agents get drained (a poisoned tweet a bot executed). Returns injection_suspected + a do_not_proceed/caution/proceed read; surfaces any addresses/links to verify separately. fingers never obeys the content -- it treats it as untrusted data.
1 trials · measured 8 days ago
check_instruction scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against co.fingersai/fingers, 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
- 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/944a21ca-17bd-4c41-ae63-9856771b2a31)