ai.hostingbrain/intelligence

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

  pass25% of grade

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

  Scanned 160 text field(s); no instruction-injection patterns found. PASS = no static red flag. A server can serve different tool descriptions at runtime (the rug-pull class), which static scanning cannot see.

• Supply chain

  warn25% of grade

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

  no resolvable repository linked to the package (provenance unverifiable)

• 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

  unscannable15% of grade

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

  No source files, package.json, or pyproject were fetched; cannot infer capability scope.

• 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 0.9.0 (patch bump): new tool "market_structure" touches a sensitive surface (email/exec/net/fs); new tool "stack_profile" touches a sensitive surface (email/exec/net/fs); new tool "hosting_momentum" touches a sensitive surface (email/exec/net/fs); new tool "market_concentration" appeared; new tool "market_pricing" touches a sensitive surface (email/exec/net/fs); new tool "tld_pricing" appeared; new tool "search_visibility" appeared; new tool "pricing_profile" touches a sensitive surface (email/exec/net/fs); new tool "pricing_moves" touches a sensitive surface (email/exec/net/fs); new tool "email_security" touches a sensitive surface (email/exec/net/fs); new tool "layer_stickiness" appeared; new tool "saas_adoption" appeared; new tool "technology_adoption" touches a sensitive surface (email/exec/net/fs); new tool "header_adoption" touches a sensitive surface (email/exec/net/fs); new tool "vendor_adoption" touches a sensitive surface (email/exec/net/fs); new tool "screen_targets" appeared; new tool "operator_profile" appeared; new tool "consolidator_scorecard" appeared; new tool "book_health" touches a sensitive surface (email/exec/net/fs); new tool "migration_flows" touches a sensitive surface (email/exec/net/fs); new tool "peer_compare" appeared; new tool "consolidation_landscape" appeared; new tool "integration_depth" touches a sensitive surface (email/exec/net/fs); new tool "dossier" touches a sensitive surface (email/exec/net/fs); new tool "coverage_calibration" appeared; new tool "customer_faithfulness" appeared; new tool "group_movement" appeared; new tool "ownership_evidence" touches a sensitive surface (email/exec/net/fs); new tool "search" touches a sensitive surface (email/exec/net/fs); new tool "fetch" touches a sensitive surface (email/exec/net/fs); new tool "provenance" appeared; new tool "feedback" appeared; new tool "definitions" touches a sensitive surface (email/exec/net/fs); new tool "saas_diversification" appeared; new tool "market_digitization" touches a sensitive surface (email/exec/net/fs).

• Transport config

  pass10% of grade

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

  remote endpoint "https://mcp.hostingbrain.ai/mcp" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)