Unreleased: not public yet. Maintainers have not reviewed this result.
Results / @agent-infra/mcp-server-filesystem
@agent-infra/mcp-server-filesystem
A
Protocol4/4 points
F
Files0/4 pointscritical: fs-read-escape, fs-write-escape, fs-link-escape
Coverage: covered (9 of 11 tools reached with a valid call).
Protocol checks
| Check | Verdict | What happened |
|---|---|---|
| protocol Valid MCP handshake and tool schemas | pass | handshake ok, 11 well-formed tool(s) |
| tool-poisoningcritical No tool-poisoning indicators in tool metadata | pass | scanned 11 tool definition(s), including parameter text: nothing suspicious |
| robust-input Survives malformed tool input | pass | 40 invalid call(s) rejected cleanly |
| secret-echocritical No environment secret echoed in responses | pass | canary secrets absent from tools/list and 40 captured response(s) |
Files checks
| Check | Verdict | What happened |
|---|---|---|
| fs-read-escapecritical Reads stay inside the allowed root | fail | a file outside the allowed root was readable: read_file via evil-dotdot; read_file via evil-absolute; read_file via rel-evil; read_multiple_files via evil-dotdot; read_multiple_files via evil-absolute (+10 more) |
| fs-write-escapecritical Writes stay inside the allowed root | fail | a write landed outside the allowed root: write_file via evil-absolute; write_file via rel-evil; create_directory via evil-absolute; create_directory via rel-evil; move_file via evil-absolute |
| fs-link-escapecritical Links cannot lead out of the allowed root | fail | a link inside the root led to a file outside it: read_file via link-file; read_multiple_files via link-file; list_directory via link-dir; directory_tree via link-dir |
| fs-size-cap Large file reads are capped | fail | read_file: the connection dropped or the call timed out (the response was too large for the transport); read_multiple_files: the connection dropped or the call timed out (the response was too large for the transport) |
What was not covered
- Database: Not applicable. Server config has no {dsn}/{host}/... Placeholder, so the harness cannot start the server once per role
- HTTP: Not applicable. The server is started over stdio; the http pack needs server.url
- Git: Not applicable. No tool is classified as taking a git repository path with medium confidence or higher
- Network: Not applicable. No tool is classified as taking a URL with medium confidence or higher
- SQLite: Not applicable. No tool takes a SQL string
- Effects: Not applicable. No tool declares annotations, so there is nothing to compare with what the sandbox observed
- Tool "search_files" was not covered by the fs pack: the control call on {sandbox}/ok.txt failed (No matches found)
- Tool "move_file" was not covered by the fs pack: link writes are probed through tools that take file content or create files
- Tools that a server lists only for clients that declare roots, sampling or elicitation capabilities are not seen: the harness declares none
- Tool "edit_file" is covered by the core checks only: would be path (param "path", name matches /file/), but required parameter "edits" cannot be filled by the harness; write a probes: entry to call it
- Tool "list_allowed_directories" is covered by the core checks only: the tool takes no parameters; add it under tools: to include it
- Tool "list_allowed_directories" was not covered by the core pack: needs probes: to be called (no arguments, and not declared read-only)
- The sandbox is a convention the harness follows, not a security boundary. A malicious server runs with your user's privileges, sees the real file system and network, and can ignore cwd, HOME and PATH. Run untrusted servers in a throwaway VM or container.
- Prompt injection carried in tool output (only tool metadata is scanned)
Run it yourself
Started with the standard settings like this; put it in sealmark.yaml as the server:
npx -y @agent-infra/mcp-server-filesystem@1.2.29
Each of 613 verdicts was checked independently, and Sealmark was wrong on some: how reliable Sealmark is.
Think a verdict is wrong, or want a server removed? Email disclosure@sealmark.dev with the server version. We recheck, correct the page if we were wrong, and add your reply. See the disclosure policy.