MCP servers that fail: no command-injection sinks
568 of the 22,160 Model Context Protocol servers where this control could be evaluated fail it — that is 3% of the evaluated corpus on the Canopii Trust Index.
- Servers failing
- 568
- Failure rate
- 3%
- Average score when failing
- 15/100
A further 207 servers warn on this control — a weaker signal we could not confirm, counted at half weight rather than as a failure.
Why this matters
Untrusted tool input reaching a shell yields remote code execution.
How to pass it
Never pass tool arguments to a shell; use argv arrays with shell disabled.
Control id code.no_command_injection — a guard control, so a confirmed failure caps the server's score at the critical ceiling no matter what else passes.
Affected servers
We publish this count, not a list of targets. A confirmed critical-severity failure of this control is a directly exploitable weakness. Each affected server's own page carries its result and evidence, so nothing is hidden from someone evaluating a specific server — but we will not publish a ranked list of exploitable systems, which is a different artifact serving a different reader.
Running one of these? The directory and the open-source scanner will tell you where you stand.
This control is one of 29 in the published rubric — see how scoring works or how the ecosystem fails every other control.