io.github.yamantaka520/agent-memory-os

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.

  Python build script has no build-time network/exec; 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. src/agent_memory_os/client.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 (scripts/validation_run.py: subprocess.* call; src/agent_memory_os/cli.py: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (scripts/validation_run.py: subprocess.* call; scripts/validation_run.py: destructive filesystem call (shutil.rmtree/os.remove/etc.)). discloses shell/exec capability: 4 files (scripts/validation_run.py, src/agent_memory_os/cli.py, src/agent_memory_os/service.py, +1 more) discloses broad/destructive filesystem access: scripts/validation_run.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: scripts/verify_acl_identities.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: scripts/verify_downgrade_compatibility.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) 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 1.8.2 (minor bump): new capability primitive(s) in source: fs-write, http-client, net, subprocess; new hardcoded outbound host/BCC destination(s): evil, host, peer, peer-b, peer2, peer3, peer4, pypi.org, static.modelcontextprotocol.io, unreachable.

• 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 telemetry behavior — disclosure