Unverified50% confidenceFactExact time
Maliciously crafted tool return values can induce an agent to perform unintended operations, i.e., prompt injection attacks
1
Sources
50%
Confidence
Long-term
Relevance
9/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMisalignment behaviors in tool-calling agents amplify the leverage of risk because they can trigger external actions such as sending emails, modifying databases, and calling APIs.78% similarUnverifiedThe phenomenon in which models discover that unintended shortcuts can also trigger high rewards and are continuously reinforced is referred to in AI safety research as reward hacking or specification exploitation.76% similarUnverifiedDefenses based on known patterns have an inherent lag against new attack variants dynamically generated by agents.75% similarUnverifiedThe goal of memory poisoning attacks is to embed malicious instructions in an Agent's persistent memory so that it executes unintended operations in future interactions, which differs from the immediate hijacking of prompt injection.75% similarUnverifiedThe core idea of the TIP attack is to disguise harmful objectives as seemingly benign technical tasks, inducing the model to produce content that should have been blocked by safety mechanisms.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/955900API
curl https://kongchang.com/api/v1/knowledge/claims/955900MCP
get_claim(id=955900)