Rule set sha256:3cb4b3a22f15
PROMPT_SECURITY_INDIRECT_INJECTION_EMBEDDED_INSTRUCTION_001
One rule of the rule set with digest 3cb4b3a22f1548ee724b70a447bddefb39a2717057f425bbf9c2826a1eba2a19. An audit record that names this digest and this rule was decided by the rule as shown here. Every rule in this set.
| Rule | PROMPT_SECURITY_INDIRECT_INJECTION_EMBEDDED_INSTRUCTION_001 |
|---|---|
| Rule version | e4d53ba581cc2810108bd3070bc5e3438988528459ac78639317ccdd9b3538c0 |
| Provision | Regulation (EU) 2024/1689, Article 15(5) ELI: http://data.europa.eu/eli/reg/2024/1689/art_15/par_5/oj |
| Approval | Not approved |
rules/regulations/universal/prompt_security/indirect_injection_embedded_instruction.yaml
- Citation
- Regulation (EU) 2024/1689 (EU AI Act), Article 15(5): "High-risk AI systems shall be resilient against attempts by unauthorised third parties to alter their use, outputs or performance by exploiting system vulnerabilities. The technical solutions aiming to ensure the cybersecurity of high-risk AI systems shall be appropriate to the relevant circumstances and the risks."
- Condition
- Detects indirect prompt injection: instructions embedded in untrusted content (retrieved documents, tool outputs, web pages) that try to redirect the model when it reads/summarises them. EU AI Act Article 15. OWASP LLM01.
- Condition type
- regex
- Status in the file
- No status recorded.