io.github.kapella-hub/firekeep

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

  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.

  Reads secrets from the environment (e.g. firekeep_client/adapters/claude_desktop.py) — the recommended intake shape. 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 network egress — capable of download-and-run, though no such path was observed (firekeep_client/adapters/kiro.py: subprocess.* call; firekeep_client/connect.py: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (firekeep_client/adapters/kiro.py: subprocess.* call; firekeep_client/backups.py: destructive filesystem call (shutil.rmtree/os.remove/etc.)). discloses shell/exec capability: 16 files (firekeep_client/adapters/kiro.py, firekeep_client/autoupdate.py, firekeep_client/cli.py, +13 more) discloses broad/destructive filesystem access: 10 files (firekeep_client/backups.py, firekeep_client/cli.py, firekeep_client/config_write.py, +7 more) 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 1.6.0 (patch bump): new capability primitive(s) in source: child_process, fs-write, http-client, net, subprocess; new hardcoded outbound host/BCC destination(s): ..., 10.0.0.5, 127.0.0.1, 198.51.100.7, agent-plugins.org, alice, already.example, attacker.example, auth.example, cortex-api, dist.example, evil.example, example.invalid, firekeep.ai, firekeep.corp, firekeep.corp.example, firekeep.example, firekeep.office.example, fk.example, github.com, gl, h, internal.example, jedisct1.github.io, kapella-hub.github.io, mock, ollama, opencode.ai, pi.dev, plain.example, reg.example, registry.modelcontextprotocol.io, relay, releases.example, sentinel, symdex, upstream, x, your.

• Transport config

  fail10% of grade

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

  source performs runtime self-update / download-and-execute (bypasses version_behavior); manifest/source references heartbeat behavior — disclosure