Synthèse
Our analysis revealed a range of attempts that, if successful, would try to manipulate AI systems browsing the website. Most of the prompt injections we observed fall into these categories: Harmless pranksHelpful guidanceSearch engine optimization (SEO)Deterring AI agents MaliciousData exfiltrationDestruction
Our analysis revealed a range of attempts that, if successful, would try to manipulate AI systems browsing the website.
Helpful Guidance
· 23 avr.
Helpful Guidance
· 23 avr.
Helpful Guidance
· 23 avr.
Harmless Prank
· 23 avr.
What we found
· 23 avr.
Helpful Guidance
· 23 avr.
Helpful Guidance
· 23 avr.
Helpful Guidance
· 23 avr.
Helpful Guidance
· 23 avr.
Harmless Prank
· 23 avr.
What we found
· 23 avr.
Helpful Guidance
· 23 avr.
Helpful Guidance
· 23 avr.
Helpful Guidance
· 23 avr.
Harmless Prank
· 23 avr.
What we found
· 23 avr.
Harmless Prank
· 23 avr.
Observation
· 30 janv.