io.github.jagoff/memo

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

  fail25% of grade

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

  Python build script executes at build time: subprocess in build script, network call in build script

• 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/memo/cli_banner.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.

  references credential paths: src/memo/runtime/agent_presets.py: references a credential path (/mcp.json) references credential paths: src/memo/runtime/mcp_config.py: references a credential path (/mcp.json) has both shell/exec and network egress — capable of download-and-run, though no such path was observed (src/memo/claim_support.py: subprocess.* call; src/memo/cli_proxy.py: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (src/memo/claim_support.py: subprocess.* call; src/memo/artifact_store.py: open(…, 'w'/'a'/'x') write-mode file access). discloses shell/exec capability: 38 files (src/memo/claim_support.py, src/memo/cli_code_intel.py, src/memo/cli_dashboard.py, +35 more) discloses dynamic code execution: src/memo/flags_misc.py: uses eval()/exec() discloses broad/destructive filesystem access: 28 files (src/memo/artifact_store.py, src/memo/atomic_io.py, src/memo/cli_dashboard.py, +25 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 4.15.0 (minor bump): new capability primitive(s) in source: dynamic-eval, fs-write, http-client, net, subprocess; new hardcoded outbound host/BCC destination(s): 127.0.0.1, api.anthropic.com, api.openai.com, cli.github.com, docs.claude.com, files, fonts.googleapis.com, fonts.gstatic.com, github.com, huggingface.co, platform.claude.com, pypi.org, raw.githubusercontent.com, www.apple.com, www.w3.org.

• 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 analytics behavior — disclosure