io.github.Blahaj-gif/hitl-finance-mcp

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_data_integrity.py: assigns a literal to secret (cafe…be (len 32)) — non-provider secret literal; prefer environment intake. Reads secrets from the environment (e.g. .env.example) — 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 (dashboard/alert_manager.py: subprocess.* call; dashboard/brokers/ibkr.py: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (dashboard/alert_manager.py: subprocess.* call; dashboard/barcache.py: destructive filesystem call (shutil.rmtree/os.remove/etc.)). discloses shell/exec capability: dashboard/alert_manager.py: subprocess.* call discloses shell/exec capability: dashboard/cli.py: subprocess.* call discloses broad/destructive filesystem access: dashboard/barcache.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: dashboard/capabilities.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 0.3.0 (patch bump): new capability primitive(s) in source: child_process, fs-write, http-client, subprocess; new hardcoded outbound host/BCC destination(s): api.bls.gov, api.ibkr.com, api.stlouisfed.org, apps.bea.gov, data-api.ecb.europa.eu, data.bls.gov, data.sec.gov, efts.sec.gov, example.com, example.gov, fred.stlouisfed.org, fredaccount.stlouisfed.org, gateway.saxobank.com, github.com, live.logonvalidation.net, sec.gov, sim.logonvalidation.net, www.bankofengland.co.uk, www.bea.gov, www.bls.gov, www.federalreserve.gov, www.sec.gov.

• Transport config

  warn10% of grade

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

  manifest/source references Analytics behavior — disclosure