io.github.FixemBCN/mcp-bifrost

What we checked

Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.

• Injection surface

  unscannable25% of grade

  Tool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).

  No tool descriptions, server instructions, prompts, or resources were fetched; nothing to scan for injection.

• Supply chain

  pass25% of grade

  Package provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.

  Python build script has no build-time network/exec; repository linkage verified

• Credential hygiene

  warn15% of grade

  How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

  tests/test_heimdall.py: embeds a PRIVATE KEY block. (in an example/sample file — lower severity, but a real key here still leaks.) tests/test_heimdall.py: assigns a literal to password (hunt…zy (len 12)) — non-provider secret literal; prefer environment intake. tests/test_heimdall.py: assigns a literal to secret (your…re (len 16)) — non-provider secret literal; prefer environment intake. tests/test_heimdall.py: assigns a literal to secret (hunt…zy (len 12)) — non-provider secret literal; prefer environment intake. Reads secrets from the environment (e.g. mcp_bifrost/server.py) — the recommended intake shape.

• Permission scope

  warn15% of grade

  Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

  has both shell/exec and network egress — capable of download-and-run, though no such path was observed (mcp_bifrost/languages/php.py: subprocess.* call; mcp_bifrost/worker.py: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (mcp_bifrost/languages/php.py: subprocess.* call; mcp_bifrost/languages/php.py: open(…, 'w'/'a'/'x') write-mode file access). discloses shell/exec capability: mcp_bifrost/languages/php.py: subprocess.* call discloses shell/exec capability: mcp_bifrost/patcher.py: subprocess.* call discloses shell/exec capability: mcp_bifrost/vcs.py: subprocess.* call discloses broad/destructive filesystem access: mcp_bifrost/languages/php.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: mcp_bifrost/languages/php.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: mcp_bifrost/patcher.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) Capability DISCLOSURE, not a verdict: static analysis sees the primitive is present and reachable, not whether its use is attacker-controlled.

• Version behavior

  fail10% of grade

  Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

  vs prior 0.1.1 (patch bump): new capability primitive(s) in source: fs-write, subprocess; new hardcoded outbound host/BCC destination(s): api.deepseek.com, github.com.

• Transport config

  unscannable10% of grade

  Remote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.

  local stdio server: no remote transport or auth surface, and no phone-home/telemetry signal found in source. Absence of transport findings is NOT a safety guarantee — phone-home hosts can be constructed at runtime and defeat static analysis.