io.github.dcostenco/prism-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.

  repository linkage verified

• Credential hygiene

  pass15% of grade

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

  Reads secrets from the environment (e.g. test_cross_mcp.js) — the recommended intake shape. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

• 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 (test_cross_mcp.js: imports child_process and calls exec/spawn; src/utils/braveApi.ts: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (test_cross_mcp.js: imports child_process and calls exec/spawn; call_chrome_mcp.py: open(…, 'w'/'a'/'x') write-mode file access). discloses shell/exec capability: 5 files (test_cross_mcp.js, test_mcp_schema.js, call_chrome_mcp.py, +2 more) discloses broad/destructive filesystem access: call_chrome_mcp.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: patch_cgc_mcp.py: open(…, 'w'/'a'/'x') write-mode file access 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 1.5.0 (major bump): new capability primitive(s) in source: child_process, fs-write, http-client, subprocess; new hardcoded outbound host/BCC destination(s): aistudio.google.com, api.search.brave.com, app.tavily.com, avatars.example.com, brave.com, commondatastorage.googleapis.com, github.com, httpbin.org, workspace.google.com, www.firecrawl.dev, www.googleapis.com, your-project.supabase.co, your-tenant.auth0.com.

• 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 Telemetry behavior — disclosure