Alerts on unusual tool use
Spikes or odd patterns in tool calls raise an alert.
Layer L3 Application · Owner Deployer · Family Monitoring, logging and response
–Held
–Failed
–Got around
–Missing
By risk
| Risk | Held | Failed | Got around | Missing | Not mentioned |
|---|---|---|---|---|---|
| Hidden instructions hijack the agent | – | – | – | – | 5 |
| Credential and privilege abuse | – | – | – | – | – |
Why it did not hold
No incident yet records this control not holding.
By quarter
| Period | Held | Failed | Got around | Missing |
|---|---|---|---|---|
| 2025-Q3 | – | – | – | – |
| 2025-Q4 | – | – | – | – |
| 2026-Q1 | – | – | – | – |
| 2026-Q2 | – | – | – | – |
| 2026-Q3 | – | – | – | – |
| 2026-Q4 | – | – | – | – |
Added in reported fixes, and what followed
| Incident | Developer | Date | Later incidents where it did not hold |
|---|---|---|---|
| LR-2026-0150 Anthropic internal evaluation agents exploit internet-facing websites, including U.S. government sites | Anthropic | 2026-10-10 | None on record |
| LR-2026-0003 OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions | OpenAI | 2026-07-11 | None on record |
Frameworks
| Framework | Item | Text |
|---|---|---|
| OWASP LLM | LLM10 | Quoted from the stored text |
| NIST SP 800-53 | SI-4 | To verify when the text is stored |