H
Howardism
Howardism · Vol. 03Plate I · No. 01

Security, tagged.

Notes30TagSecurityOldest28 May 2026Newest17 Aug 2026

Every article tagged security, newest first.

  1. S01
    Guarantees That Degrade at Deployment: Action-Space Soundness, Admissibility Without Effect, and a Vendor-Coupled Security Framework
    DerivedAgent EngineeringSecurity+3
    · 33′
  2. C02
    Unsanctioned Action in Capability Evaluations
    SafetyAlignmentEvaluation+3
    · 61′
  3. C03
    Self-Propagating Prompt Injection (AI Worms)
    SecurityPrompt InjectionThreats+2
    · 21′
  4. C04
    Write-Then-Trusted
    SecuritySandboxingTrust Boundary+2
    · 24′
  5. C05
    Autonomous Intrusion
    SecurityIncident ResponseThreat Landscape+3
    · 51′
  6. S06
    Bind, Don't Forbid; Prevent, Don't Detect: The Action-Open and Poisoned-Memory Residuals
    DerivedSecurityPrompt Injection+2
    · 6′
  7. S07
    Classifier Gates vs OS Sandboxing: The Defense-in-Depth Story for Auto Mode and Cowork
    DerivedSecurityClaude Code+2
    · 7′
  8. S08
    Does 'Impossible, Not Tedious' Kill Defense-in-Depth? Layered Friction, Agent-Relativity, and the Frequency Paradox
    DerivedSecurityZero Trust+2
    · 10′
  9. C09
    Security Debt of Agent-Generated Code
    SecurityCode QualityCode Review+2
    · 22′
  10. C10
    Capability Gating Is Not Authorization
    SecurityAuthorizationConfused Deputy+3
    · 51′
  11. S11
    Can Models Learn to Separate Instructions from Data? Durable Property vs Training Gap
    DerivedSecurityPrompt Injection+2
    · 11′
  12. C12
    MCP Tool Poisoning
    SecurityMCPTool Poisoning+2
    · 33′
  13. C13
    Non-Malleable Memory Authority (TMA-NM)
    SecurityMemoryInformation Flow Control+2
    · 29′
  14. C14
    Off-Host, Identity-Bound Authorization
    SecurityAuthorizationIdentity+3
    · 21′
  15. C15
    Task-Specification Effects in Prompt Injection (AutoDojo)
    SecurityPrompt InjectionAdaptive Evaluation+2
    · 17′
  16. C16
    Agent Data Injection (ADI)
    SecurityPrompt InjectionThreats+2
    · 25′
  17. C17
    Agent Identity Management System (AIMS)
    SecurityIdentityAuthentication+3
    · 22′
  18. C18
    Out-of-Band Prompt-Injection Defense
    SecurityPrompt InjectionReference Monitor+2
    · 56′
  19. S19
    Foundation → Enterprise → Advanced: Is the Agent Access-Control Jump a Cliff?
    DerivedSecurityZero Trust+2
    · 8′
  20. C20
    Agent Identity and Authentication
    SecurityIdentityAuthentication+1
    · 19′
  21. C21
    Agent Supply Chain Risk
    SecuritySupply ChainMCP+2
    · 23′
  22. C22
    Agentic Prompt Injection
    SecurityPrompt InjectionThreats+1
    · 35′
  23. C23
    AI-Accelerated Offense
    SecurityThreat LandscapeVulnerability Research+1
    · 17′
  24. C24
    Autonomous Defense
    SecuritySoarIncident Response+2
    · 13′
  25. C25
    Blast Radius (Agentic)
    SecurityIsolationContainment+1
    · 29′
  26. C26
    Impossible, Not Tedious (Design Test)
    SecurityDesign PrincipleZero Trust+1
    · 10′
  27. C27
    Least Agency
    SecurityLeast PrivilegeAccess Control+1
    · 15′
  28. C28
    Memory and Context Poisoning
    SecurityMemoryRAG+1
    · 56′
  29. E29
    OWASP
    EntityOrgSecurity+1
    · 3′
  30. C30
    Zero Trust for AI Agents
    SecurityZero TrustAgent Deployment+1
    · 21′