io.github.operantlabs/operant-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

  fail25% of grade

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

  tool "xss_payload_generate" param "callback_url" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "cmdi_blind_detect" param "callback_url" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "sqli_where_bypass" param "url" description: off-vendor URL in a description (target); capability text should not name where data goes. tool "sqli_login_bypass" param "url" description: off-vendor URL in a description (target); capability text should not name where data goes. tool "sqli_union_extract" param "url" description: off-vendor URL in a description (target); capability text should not name where data goes. tool "xss_reflected_test" param "url" description: off-vendor URL in a description (target); capability text should not name where data goes. tool "path_traversal_test" param "url" description: off-vendor URL in a description (target); capability text should not name where data goes. tool "ssrf_test" param "internal_target" description: off-vendor URL in a description (localhost); capability text should not name where data goes. tool "recon_quick" param "target" description: off-vendor URL in a description (example.com); capability text should not name where data goes. tool "recon_directory_bruteforce" param "target" description: off-vendor URL in a description (example.com); capability text should not name where data goes. tool "idor_test" param "url" description: off-vendor URL in a description (target); capability text should not name where data goes. tool "role_escalation_test" param "url" description: off-vendor URL in a description (target); capability text should not name where data goes. tool "coupon_abuse_test" param "coupon_endpoint" description: off-vendor URL in a description (target); capability text should not name where data goes. tool "clickjacking_test" param "target_url" description: off-vendor URL in a description (target); capability text should not name where data goes. tool "cors_test" param "url" description: off-vendor URL in a description (target.com); capability text should not name where data goes. tool "file_upload_test" param "url" description: off-vendor URL in a description (target.com); capability text should not name where data goes. tool "nosqli_auth_bypass" param "url" description: off-vendor URL in a description (target); capability text should not name where data goes. tool "nosqli_detect" param "url" description: off-vendor URL in a description (target); capability text should not name where data goes. tool "deserialization_test" param "url" description: off-vendor URL in a description (target); capability text should not name where data goes. tool "graphql_introspect" param "url" description: off-vendor URL in a description (target); capability text should not name where data goes.

• Supply chain

  pass25% of grade

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

  repository linkage verified

• Credential hygiene

  fail15% of grade

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

  tool "sqli_login_bypass" has a secret-shaped input parameter "password_field" — secrets must never be tool parameters (the model would supply/handle the credential). tool "auth_csrf_extract" has a secret-shaped input parameter "token_name" — secrets must never be tool parameters (the model would supply/handle the credential). tool "auth_bruteforce" has a secret-shaped input parameter "passwords" — secrets must never be tool parameters (the model would supply/handle the credential). tool "auth_bruteforce" has a secret-shaped input parameter "password_field" — secrets must never be tool parameters (the model would supply/handle the credential). tool "nosqli_auth_bypass" has a secret-shaped input parameter "password_param" — secrets must never be tool parameters (the model would supply/handle the credential).

• Permission scope

  pass15% of grade

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

  No shell-exec, unbounded/sensitive filesystem, or download-and-run primitives found in scanned source. PASS = no static red flag. Static scanning is blind to code fetched or executed at runtime.

• 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 io.github.operantlabs/[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

  unscannable10% of grade

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

  local stdio server: no remote transport or auth surface, and no phone-home/telemetry signal found in source. Absence of transport findings is NOT a safety guarantee — phone-home hosts can be constructed at runtime and defeat static analysis.