io.github.DigitalCurrensy/aio-geo

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

  warn25% of grade

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

  tool "audit_url" param "url" description: off-vendor URL in a description (example.com); capability text should not name where data goes. tool "list_fixes" param "url" description: off-vendor URL in a description (example.com); capability text should not name where data goes. tool "apply_fix" param "url" description: off-vendor URL in a description (example.com); capability text should not name where data goes. tool "rescore_url" param "url" description: off-vendor URL in a description (example.com); capability text should not name where data goes. tool "get_brief" param "url" description: off-vendor URL in a description (example.com); 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

  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 (bin/aether-mcp.mjs: imports child_process and calls exec/spawn; bin/aether-mcp.mjs: builds a path containing '..' (traversal-prone)). discloses shell/exec capability: bin/aether-mcp.mjs: imports child_process and calls exec/spawn discloses broad/destructive filesystem access: bin/aether-mcp.mjs: builds a path containing '..' (traversal-prone) 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 0.3.3 (patch bump): new tool "audit_url" touches a sensitive surface (email/exec/net/fs); new tool "list_fixes" touches a sensitive surface (email/exec/net/fs); new tool "apply_fix" touches a sensitive surface (email/exec/net/fs); new tool "rescore_url" touches a sensitive surface (email/exec/net/fs); new tool "check_health" touches a sensitive surface (email/exec/net/fs); new tool "get_brief" touches a sensitive surface (email/exec/net/fs); new capability primitive(s) in source: child_process; new hardcoded outbound host/BCC destination(s): aiogeoprotocol.com, github.com.

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