UTC

OWASP Top 10 for LLM Applications 2026

LLM08:2026 Hidden Context Exposure

None of its primary CWEs is specific to it, so ShieldMap does not tag advisories with it, and 1 technique page explains how the attacks work.

OWASP Top 10 for Agentic Applications
  • ●ASI06:2026 Memory & Context PoisoningLLM08's scope explicitly defers "the agentic amplifications of this risk, e.g., persistent memory, inter-agent channels, tool configuration persistence, and multi-step agent compromise" to the OWASP Top 10 for Agentic Applications; ASI06 is the pointer for persistent-memory poisoning building on exposed hidden context, not an equivalent risk.
  • ●ASI07:2026 Insecure Inter-Agent CommunicationSame scope carve-out names "inter-agent channels" as an out-of-scope amplification; ASI07 is the pointer for hidden-context material propagating across agent-to-agent messaging, not an equivalent risk.
CWE weaknesses
  • ●CWE-200 Exposure of Sensitive Information to an Unauthorized ActorThe entry is defined by unauthorized extraction, inference, or reconstruction of hidden system instructions and operational context.
  • ○CWE-798 Use of Hard-coded CredentialsAPI keys, tokens, and connection strings embedded in the system prompt are the highest-severity credential exposure.
  • ○CWE-693 Protection Mechanism FailureRefusal and behavior-control instructions placed in hidden context are reverse-engineered and bypassed rather than enforced.
  • ○CWE-285 Improper AuthorizationAuthorization and access control must be enforced independently of the model, since roles and permissions carried in tool descriptions leak and fail.
MITRE ATLAS tactics
  • ●AML.TA0008 DiscoveryThe attack extracts and reconstructs the system prompt, tool list, roles, and refusal logic, discovering the AI system's hidden configuration.
  • ●AML.TA0010 ExfiltrationLeaking that hidden context across the trust boundary is model data leakage, moving configuration the operator meant to keep private into the attacker's hands.
  • ○AML.TA0002 ReconnaissanceExtracted context gives the attacker concrete targets for follow-on prompt injection and reconnaissance for downstream action chaining.
  • ○AML.TA0013 Credential AccessCredentials embedded in the system prompt are obtained when the hidden context leaks, handing the attacker usable secrets.
NIST AI 600-1 risks
  • ●NIST Information SecuritySystem-prompt and context extraction, an expanded attack surface, and lowered barriers to targeted exploitation are the core security risks.
  • ○NIST Intellectual PropertyExposed hidden context can reveal proprietary behavior and sensitive implementation details, such as a leaked system prompt.
NIST AI RMF categories
  • ○MEASURE 2 evaluate trustworthinessDetecting hidden-context exposure is a security-evaluation activity, red-teaming for prompt and context extraction grounded in RL-based red-teaming for privacy leakage and system-prompt-extraction research.
OWASP GenAI Data Security
  • ○DSGAI18 Inference & Data ReconstructionThe entry is defined by extraction, inference, and reconstruction of hidden context, the same reconstruction attacks that recover a system prompt from model behavior.
  • ○DSGAI15 Over-Broad Context Windows & Prompt Over-SharingThe central preventive principle is to keep sensitive data out of hidden context and assume all context is discoverable.
  • ○DSGAI02 Agent Identity & Credential ExposureAPI keys and tokens embedded in hidden context are harvested once an attacker extracts that context.
OWASP AIVSS agentic risks
  • ○AIVSS-2 Agent Access Control ViolationDisclosed permission rules and user-role directives from hidden context reveal the authorization model, inviting probing that bypasses controls the application should enforce independently of the LLM.
  • ○AIVSS-1 Agentic AI Tool MisuseExtracting the hidden tool list and parameter schemas gives an attacker concrete targets to steer the application toward specific tool calls.
CSA AI Controls Matrix domains
  • ●AIS Application & Interface Security
  • ○IAM Identity & Access Management
  • ○CEK Cryptography, Encryption & Key Management

Mappings and their reasons from the OWASP Top 10 for LLM Applications 2026, Appendix A (OWASP GenAI Security Project), shared under CC BY-SA 4.0. Mappings restructured as data; the ATT&CK section and the AICM relevance text left out. Navigation, not a compliance claim.