io.github.tuanle96/mcp-odoo

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

  warn15% of grade

  How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

  tests/test_audit.py: assigns a literal to token (odoo…23 (len 17)) — non-provider secret literal; prefer environment intake. tests/test_odoo_client.py: assigns a literal to password (demo…rd (len 13)) — non-provider secret literal; prefer environment intake. tests/test_odoo_client.py: assigns a literal to password (lega…rd (len 15)) — non-provider secret literal; prefer environment intake. Reads secrets from the environment (e.g. scripts/benchmark_head_to_head.py) — the recommended intake shape.

• Permission scope

  fail15% of grade

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

  HIGH: shell/exec capability AND network egress together — download-and-execute risk (scripts/odoo_compose_smoke.py: subprocess.* call; scripts/odoo_compose_smoke.py: outbound HTTP/socket call). HIGH: shell/exec capability AND destructive filesystem writes together (scripts/odoo_compose_smoke.py: subprocess.* call; scripts/benchmark_tools.py: path traversal ('../') combined with file access). discloses shell/exec capability: scripts/odoo_compose_smoke.py: subprocess.* call discloses shell/exec capability: scripts/odoo_multi_instance_smoke.py: subprocess.* call discloses broad/destructive filesystem access: scripts/benchmark_tools.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: scripts/odoo_multi_instance_smoke.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: tests/test_tool_helpers.py: 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 1.2.1 (patch bump): new capability primitive(s) in source: fs-write, http-client; new hardcoded outbound host/BCC destination(s): as.example.com, demo.odoo.com, evil.example.com, mcp.erpipe.com, mcp.example.com, mycompany.odoo.com, other.example.com.

• 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 tracking behavior — disclosure