com.boosthis/boosthis

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

  fail25% of grade

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

  tool "boosthis_vigilance" description: text addressed to the model rather than describing a capability. tool "boosthis_get_integration_kit" description: off-vendor URL in a description (www.boosthis.com); capability text should not name where data goes. tool "boosthis_get_integration_kit" param "runtime" description: off-vendor URL in a description (www.boosthis.com); capability text should not name where data goes. tool "boosthis_check_for_update" description: off-vendor URL in a description (www.boosthis.com); capability text should not name where data goes. tool "boosthis_verify_kit_install" description: off-vendor URL in a description (www.boosthis.com); capability text should not name where data goes. server instructions: off-vendor URL in a description (www.boosthis.com); capability text should not name where data goes.

• 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

  fail15% of grade

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

  tool "boosthis_session_summary" has a secret-shaped input parameter "read_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "boosthis_recent_samples" has a secret-shaped input parameter "read_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "boosthis_budgets" has a secret-shaped input parameter "read_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "boosthis_what_should_i_look_at_next" has a secret-shaped input parameter "read_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "boosthis_snapshot" has a secret-shaped input parameter "read_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "boosthis_crash_risk" has a secret-shaped input parameter "read_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "boosthis_full_stack_trace" has a secret-shaped input parameter "read_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "boosthis_maintenance_mix" has a secret-shaped input parameter "account_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "boosthis_trend" has a secret-shaped input parameter "read_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "boosthis_vigilance" has a secret-shaped input parameter "read_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "boosthis_jobs" has a secret-shaped input parameter "read_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "boosthis_alerts" has a secret-shaped input parameter "account_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "boosthis_remember_promise" has a secret-shaped input parameter "account_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "boosthis_check_claim" has a secret-shaped input parameter "account_token" — secrets must never be tool parameters (the model would supply/handle the credential).

• 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

  unscannable10% of grade

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

  no prior version to diff (first sight of com.boosthis/[email protected]); version-drift / rug-pull cannot be evaluated. Cold-start risk is covered by point-in-time checks (injection_surface, supply_chain, credential_hygiene), not here.

• 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://www.boosthis.com/mcp" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)