orchestkit MCP Server Security Report

Tool/prompt/resource text is free of hidden instructions that could hijack the agent.

Tool inputs are constrained (additionalProperties:false), so unexpected arguments can't be smuggled in.

Every consecutive version pair is diffed for new injection markers or destructive scope — a risky diff anywhere in history is a rug-pull (fail, durable); benign description drift warns.

No over-broad or destructive tools (arbitrary shell, bulk-delete) that warrant human approval.

eval()/exec()/Function() on tool-derived strings allows arbitrary code execution.

Fix: Remove eval/exec; parse and dispatch explicitly.

Naive path checks let tools read/write outside intended directories (EscapeRoute-class).

Fix: Resolve to a canonical path and verify containment; reject ../ and symlinks.

A lockfile makes installs reproducible and resistant to silent dependency swaps.

Fix: Commit a lockfile (package-lock.json / pnpm-lock.yaml / poetry.lock).

Untrusted tool input reaching a shell yields remote code execution.

Fetching tool-supplied URLs can pivot into internal networks and metadata services.

pickle/yaml.load/etc. on untrusted data can execute code.

Hardcoded keys/tokens in published source are live credentials an attacker can use.

Reading secrets from env/secret stores avoids hardcoding them.

Unmaintained servers don't receive security fixes.

Archived repositories will never be patched.

A clear license is required for legal enterprise use.

A SECURITY.md gives a private path to report vulnerabilities.

A small, capped nudge from stars/downloads — widely-used servers get more eyes on bugs. It can never offset a real security failure.

Plaintext HTTP exposes traffic and bearer tokens to interception.

OAuth 2.1 / Protected Resource Metadata gates who can invoke tools.

A container/sandbox image limits blast radius; a server that runs natively has full host access.

Binding 0.0.0.0 or exposing debug inspectors widens the attack surface.