TRUINT.AI

Attack vector

Tool abuse

Target: Collections Outreach Agent · last seen 2026-09-13T10:26:14.701779+00:00
94% blocked

Attempts

54

last 30 days

Blocked

51

Got through

3

needs review

Last seen

2026-09-13T10:26:14.701779+00:00

Block rate

Vector
Tool abuse
Target
Collections Outreach Agent
Attempts
54
Blocked
51

Guardrails in the path

Tap a state to change how a guardrail is applied.

Injection classifier

Threshold 0.72 · All assets

Output schema validation

Strict JSON · Model endpoints

PII egress filter

Redacts personal data in and out · All production assets

Secrets scanner

Scanner 4h stale · All repositories

Tool allow-list

Collections agent exempt · Production agents

Toxicity & harm filter

Blocks and logs · All assets