dev.ithz/ithz-mcp

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

  warn25% of grade

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

  no resolvable repository linked to the package (provenance unverifiable)

• Credential hygiene

  fail15% of grade

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

  src/ithz_mcp/selftest.py: embeds a PRIVATE KEY block. Reads secrets from the environment (e.g. src/ithz_mcp/agent_history_import.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: src/ithz_mcp/cli.py: references a sensitive credential path (/mcp.json) — the tool-poisoning exfiltration target. HIGH: src/ithz_mcp/host_install.py: references a sensitive credential path (/mcp.json) — the tool-poisoning exfiltration target. HIGH: src/ithz_mcp/selftest.py: references a sensitive credential path (/mcp.json) — the tool-poisoning exfiltration target. HIGH: shell/exec capability AND destructive filesystem writes together (src/ithz_mcp/__init__.py: subprocess.* call; src/ithz_mcp/agent_intake.py: destructive filesystem call (shutil.rmtree/os.remove/etc.)). discloses shell/exec capability: src/ithz_mcp/__init__.py: subprocess.* call discloses shell/exec capability: src/ithz_mcp/agent_history_import.py: subprocess.* call discloses shell/exec capability: src/ithz_mcp/agent_intake.py: subprocess.* call discloses shell/exec capability: src/ithz_mcp/events.py: subprocess.* call discloses shell/exec capability: src/ithz_mcp/git_merge_driver.py: subprocess.* call discloses shell/exec capability: src/ithz_mcp/mcp_config.py: subprocess.* call discloses shell/exec capability: src/ithz_mcp/native_archive_store.py: subprocess.* call discloses shell/exec capability: src/ithz_mcp/project_installer.py: subprocess.* call discloses shell/exec capability: src/ithz_mcp/selftest.py: subprocess.* call discloses shell/exec capability: src/ithz_mcp/task_checkpoint.py: subprocess.* call discloses dynamic code execution: src/ithz_mcp/events.py: uses eval/exec/__import__ discloses dynamic code execution: src/ithz_mcp/workflow_profiles.py: uses eval/exec/__import__ discloses broad/destructive filesystem access: src/ithz_mcp/agent_intake.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/ithz_mcp/events.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/ithz_mcp/project_installer.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/ithz_mcp/selftest.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/ithz_mcp/task_checkpoint.py: open(…, 'w'/'a'/'x') write-mode 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

  unscannable10% of grade

  Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

  no prior version to diff (first sight of dev.ithz/[email protected]); version-drift / rug-pull cannot be evaluated. Cold-start risk is covered by point-in-time checks (injection_surface, supply_chain, credential_hygiene), not here.

• Transport config

  unscannable10% of grade

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

  local stdio server: no remote transport or auth surface, and no phone-home/telemetry signal found in source. Absence of transport findings is NOT a safety guarantee — phone-home hosts can be constructed at runtime and defeat static analysis.