com.openagenda/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

  warn25% of grade

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

  package name "@openagenda/mcp" is edit-distance 2 from popular package "yup" (typosquat candidate); dependency "@openagenda/logs" is edit-distance 2 from popular package "cors" (typosquat candidate); dependency "@opentelemetry/api" is edit-distance 2 from popular package "pg" (typosquat candidate); dependency "jose" is edit-distance 2 from popular package "@babel/core" (typosquat candidate); dependency "yaml" is edit-distance 2 from popular package "yarn" (typosquat candidate)

• 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. src/index.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

  fail15% of grade

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

  HIGH: src/egressPolicy.js: references a sensitive credential path (/.ssh/) — the tool-poisoning exfiltration target. HIGH: src/httpServer.js: references a sensitive credential path (/mcp.json) — the tool-poisoning exfiltration target. HIGH: src/landing.js: references a sensitive credential path (/.cursor/) — the tool-poisoning exfiltration target. HIGH: src/serverCard.js: references a sensitive credential path (/mcp.json) — the tool-poisoning exfiltration target. HIGH: src/toolDefs.js: references a sensitive credential path (/mcp.json) — the tool-poisoning exfiltration target. HIGH: shell/exec capability AND network egress together — download-and-execute risk (src/sandbox/spawn.js: imports child_process and calls exec/spawn; src/auth/assertIssuer.js: outbound HTTP/socket call). HIGH: shell/exec capability AND destructive filesystem writes together (src/sandbox/spawn.js: imports child_process and calls exec/spawn; src/auth/assertIssuer.js: path traversal ('../') combined with file access). discloses shell/exec capability: src/sandbox/spawn.js: imports child_process and calls exec/spawn discloses broad/destructive filesystem access: src/auth/assertIssuer.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/cli.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/index.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/landing.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/sandbox/executors/microsandboxExecutor.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/sandbox/preamble.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/server.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/serverCard.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/auth/verifier.js: path traversal ('../') combined with 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 1.3.1 (patch bump): new hardcoded outbound host/BCC destination(s): cdn.openagenda.com, insiders.vscode.dev, vscode.dev.

• 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