CIRIS has a new look. Visit the new site →

back to the lobby

OWASP Agentic security mapping

The OWASP Top 10 for Agentic Applications, mapped to CIRIS.

For every one of the ten agentic threats OWASP named, here is the specific CIRIS mechanism that addresses it, an honest coverage level, and a citation you can check. We map the whole taxonomy, including where we fall short.

One full, nine partial, none hand-waved. A page that claimed all ten would be exactly the marketing we tell you not to trust. The coverage levels below survived a separate skeptic whose job was to knock them down, and where a defense lives in the substrate but the deployed agent has not inherited it yet, we say so on the row.

RiskCoverageHow CIRIS addresses it
ASI01 Agent Goal HijackPartialDefense in depth: prompt-injection scanning on imported skills and messages, visual-injection isolation (conscience evaluators never see raw image bytes), and a conscience pipeline that re-checks every resulting action against the user's original intent before it fires. Gap: input scanning is pattern-based and does not formally separate retrieved data from instructions.
ASI02 Tool MisusePartialCIRISServer ships a capability-verb allow/deny list with a server-enforced never-list, checked before an operation runs, so a delegated agent cannot invoke a destructive op it was not granted. Caveat: this guards the fabric layer today and does not yet gate the deployed agent's own LLM tool calls; agent inheritance is a planned phase.
ASI03 Identity & Privilege AbusePartialScoped, delegated, revocable authority in the substrate: constraints carried in signed edges, a never-list that blocks re-delegating the highest powers so authority cannot escalate, tighten-only approval, and instant revocation. Caveat: enforced on the fabric's owner-op surface today; deployed-agent inheritance is a planned phase.
ASI04 Agentic Supply ChainPartialBuild integrity via CIRISVerify's post-quantum signed module manifests (Ed25519 + ML-DSA-65 over a full file-tree hash), plus signed, attested identity for federated components. Gap: covers CIRIS's own build and module chain, not arbitrary third-party MCP servers.
ASI05 Unexpected Code ExecutionPartialSemantic conscience gates (entropy, coherence, optimization-veto) run on every tool action before it fires, and uncertainty defers to a human. Gap: this is semantic review, not a deterministic code sandbox.
ASI06 Memory & Context PoisoningPartialEvery write to graph memory is a governed, conscience-checked action into a scoped, versioned graph, not a silent side effect, so a poisoning write is itself an auditable decision. Gap: trust-scoring of retrieved content is partial.
ASI07 Insecure Inter-Agent CommunicationPartialCIRISEdge verifies every inter-agent message through a seven-step pipeline ending in hybrid Ed25519 + ML-DSA-65 signature verification (size cap, typed deserialize, schema allow-list, destination-key check, replay window). Gap: the federation transport is still being built out.
ASI08 Cascading FailuresFullBounded at three independent layers: per-service circuit breakers (closed / open / half-open) around risky calls, the conscience pipeline stopping a bad action before it propagates, and mesh isolation measured at zero cross-group leakage across 50 to 400 nodes.
ASI09 Human-Agent Trust ExploitationPartialThe conscience pipeline scores the agent's own explanatory text, including the reason shown to a human reviewer, for overconfidence and manipulation before a human ever sees it. Gap: it audits with the same model family it is checking.
ASI10 Rogue AgentsPartialThree layers: six consciences gate every consequential action before it executes, a hash-chained signed audit trail makes concealment detectable after the fact, and the fail-secure kill switch lets named humans halt a misaligned agent. Gap: catching a subtly-misaligned-but-coherent agent is inherently bounded.

OWASP Top 10 for Agentic Applications, published December 2025. Mapped to CIRIS as of July 2026; tell us if a cell is wrong and we will fix it.

Sources
  1. ASI01 Agent Goal HijackCIRISAgent skill-import SECURITY.md + conscience pipeline
  2. ASI02 Tool MisuseCIRISServer auth/gate.rs + DELEGATION_CONSTRAINTS.md (shipped 0.5.72)
  3. ASI03 Identity & Privilege AbuseCIRISServer auth/gate.rs (never-list, tighten-only) + adoption plan
  4. ASI04 Agentic Supply ChainCIRISVerify Threat Model, §3.4 Supply Chain
  5. ASI05 Unexpected Code ExecutionCIRISAgent conscience/core.py (semantic action gates)
  6. ASI06 Memory & Context PoisoningCIRISAgent ciris_engine (governed graph memory)
  7. ASI07 Insecure Inter-Agent CommunicationCIRISEdge README (verify-before-dispatch pipeline)
  8. ASI08 Cascading FailuresCIRISAgent circuit_breaker.py + CIRISServer measured mesh isolation
  9. ASI09 Human-Agent Trust ExploitationCIRISAgent epistemic-humility conscience prompt
  10. ASI10 Rogue AgentsCIRISVerify HUMANITY_ACCORD kill switch + conscience pipeline

The taxonomy is one lens. See where CIRIS sits among every approach to AI accountability, and how the kill switch is independently verifiable.

CIRISsafe by structure · open by principle · kind by design