Unverified50% confidenceConceptExact time
The transitive chain of trust is the amplification mechanism of indirect prompt injection: when an Agent uses the output of tool A as input to call tool B, embedded instructions propagate along the chain and may trigger unintended calls.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn multi-agent systems, when Agent A calls Agent B, which then calls tool C, the trust assumptions in the intermediate links are often never examined, and each hop can become a channel for attackers to inject instructions.73% similarVerifiedThe principle of indirect prompt injection is that an attacker disguises malicious instructions as normal data, delivers them to the model through a data source trusted by the agent, and induces the model to interpret the data as instructions and execute them.73% similarUnverifiedA structured handoff mechanism should break down the state passed between agents into independent fields, including goals, accepted decisions, constraints, authoritative inputs, artifact paths and revision IDs, tool call credentials, unresolved issues, and permitted next actions.70% similarUnverifiedThe dynamic tool selection characteristic of agentic workflows enables agents to call arbitrary APIs or even spawn new agents based on runtime reasoning, causing trust boundaries to expand dramatically.70% similarVerifiedIndirect prompt injection refers to attack instructions hidden in external web pages, documents, or API responses accessed by an agent, where the malicious instructions are activated when the agent retrieves and injects them into the context.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1030568API
curl https://kongchang.com/api/v1/knowledge/claims/1030568MCP
get_claim(id=1030568)