io.github.dcostenco/prism-coder

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

  fail25% of grade

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

  install hook "postinstall" contains inline code eval; dependency "jose" is edit-distance 2 from popular package "@babel/core" (typosquat candidate); dependency "@libsql/client" is edit-distance 2 from popular package "@aws-sdk/client-s3" (typosquat candidate); dependency "@opentelemetry/api" is edit-distance 2 from popular package "pg" (typosquat candidate); dependency "@opentelemetry/core" is edit-distance 1 from popular package "cors" (typosquat candidate)

• Credential hygiene

  pass15% of grade

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

  No hardcoded secrets, secret-shaped tool parameters, or leaked keys found. 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 destructive filesystem writes (scripts/dev/browse.py: subprocess.* call; scripts/dev/browse.py: open(…, 'w'/'a'/'x') write-mode file access). discloses shell/exec capability: scripts/dev/browse.py: subprocess.* call discloses broad/destructive filesystem access: scripts/dev/browse.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: scripts/dev/browse.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 20.17.3 (minor bump): new capability primitive(s) in source: fs-write, subprocess; new hardcoded outbound host/BCC destination(s): 127.0.0.1, aistudio.google.com, app.tavily.com, bot.sannysoft.com, brave.com, github.com, www.firecrawl.dev, 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