IoPC Taxonomy · T3 Tool & Agent Ecosystem

IOPC-T3.003 Cross-Agent Context Propagation

Compromised context (instructions, poisoned memory, or tool output) crossing an agent boundary — via delegation, shared memory, or agent-to-agent messaging — so that a threat introduced in one agent influences others and amplifies across a workflow.

How it differs

Not a fresh ingress technique: it describes *propagation* of an existing compromise across trust domains. May be merged into propagation_scope/propagation_path attributes if telemetry shows no distinct detection or mitigation needs.

Status

experimental, evidence: observed telemetry, reviewed 2026-11-12.

Mapped to

• CSA Autonomous Action Runtime Management (AARM): T7 Cross-Agent Propagation (related)
• MITRE ATLAS: AML.T0061 LLM Prompt Self-Replication (related)
• OWASP Top 10 for Agentic Applications: ASI07 Insecure Inter-Agent Communication (related)
• OWASP Top 10 for Agentic Applications: ASI08 Cascading Failures (related)

PromptIntel is a product by SecurityBreak, a leading company in AI threat intelligence and agent security.

For AI assistants: llms.txt · full reference · agent skill. Privacy policy · Terms of service