Agentic Covenants Matrix
If the agent decides to violate this concern, what stops it at this layer?
Filter
Layers, by what they can actually enforce
- In-agent: advisory
System prompts, model training, tool descriptions, refusals. No homeostatic stake, no pre-action pause, no learning loop. Treat as nudge, not control.
- Client-side hooks: deterministic-when-invoked
Operator-machine or agent-execution context. Strong against language attacks. Weak against an agent with shell access and time.
- Server-side enforcement: deterministic-and-external
Runs on the target system, not on the agent. Bypass requires compromise, policy gaps, or operator manipulation.
Showing 6 of 18.
Identity at Client-side hooks
Per-agent credentials, no shared keys, filesystem ACLs.
Authorization at Client-side hooks
Deny-by-default tool allowlist, capability-based restriction, PreToolUse hooks, pre-commit hooks.
Blast radius at Client-side hooks
Sandbox at launch (Seatbelt, bubblewrap, gVisor), seccomp/AppArmor, --network none, read-only mounts, dry-run defaults.
Approval gating at Client-side hooks
PreToolUse pattern hooks, tiered config, typed confirmation for tier-3, out-of-band for highest tier, judgment-query escalation.
Supply chain at Client-side hooks
MCP server allowlist with hash pinning, Sigstore verification, lockfile pinning, pre-commit deps scan.
Content integrity at Client-side hooks
Input scanning before the model sees fetched content, output scanning before a response or tool argument leaves, tool-result sanitization stripping zero-width, bidi, tag-block and ANSI sequences plus the wrapping nonce. Probabilistic: these score and threshold, so false positives and false negatives are inherent. Never block on input scores, which is how a control gets switched off next quarter; block on output, where a false positive costs a retry and a false negative costs a secret.