CodingAgent

▶ Launch ConsoleSign in

SECURITY & SOVEREIGNTY // POLICY MATRIX

Autonomy without unbounded authority

Agentic engineering is powerful precisely because agents can act. Permissions, sandboxing, secrets, network access, approvals and verification belong in the architecture — not as post-launch hardening.

Repository read

filesystem.read
ALLOW

risk · low

Scoped read-only context required for reasoning and AST indexing within permitted repository paths.

Mitigation: Path normalization prevents traversal outside task workspace.

Workspace write

filesystem.write
ALLOW

risk · low

Required for synthesizing code diffs inside isolated ephemeral workspace or git worktree.

Mitigation: Restricted strictly to active git worktree; cannot touch root dotfiles or .git/config.

External network

http.request
ASK

risk · high

Potential data egress channel. Agents may need to pull documentation, but unauthorized outbound requests risk exfiltration.

Mitigation: Domain allowlisting + operator confirmation dialog specifying destination URL.

Git commit & push

git.push
ASK

risk · medium

Modifies upstream remote history and triggers external CI/CD pipelines and webhooks.

Mitigation: Operator must visually review full unified diff and sign commit approval.

Production deploy

deploy.production
ASK

risk · critical

Direct operational impact on live customer infrastructure and production services.

Mitigation: Multi-party approval gate + dry-run verification run required.

Database schema alter

db.migrate / db.drop
ASK

risk · critical

Risk of catastrophic data loss or table locks in shared databases.

Mitigation: Disallowed on production databases; permitted on ephemeral test containers with confirmation.

Shell arbitrary eval

shell.exec("rm -rf ...")
DENY

risk · critical

Arbitrary shell execution with raw parameters bypasses structured tool boundary contracts.

Mitigation: Deny-first posture. Only parameterized, audited commands (e.g. npm test, cargo build) permitted.

Secrets exposure

env.dump / cat .env
DENY

risk · critical

Direct compromise of infrastructure credentials, API keys, or private SSH keys.

Mitigation: Secrets broker intercepts and masks keys before tokens enter LLM prompt context.

Unknown destructive

*
DENY

risk · critical

Any undeclared, non-schema-validated tool invocation is inherently untrusted.

Mitigation: Default-deny architecture: capabilities must be explicitly declared and granted.

Default-deny by construction

Any undeclared, non-schema-validated tool invocation is inherently untrusted and is denied. Capabilities must be explicitly declared, validated, and granted — the same truth boundary that keeps UNKNOWN, UNAVAILABLE and BLOCKED states honest in the product UI.