MCP server · trust report

io.github.Isometric-Architect/ai-objective-index

1 check that ran failed — permission scope — so this release can’t be trusted as-is.

Publisher
io.github.Isometric-Architect
Repository
github.com/Isometric-Architect/ai-objective-index
Install
pypi:ai-objective-index
Versions
1
Inspected
4 of 6 checks · 65%
Scored
2026-07-21 · rubric 1.0.0

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.

6 checks1 clean3 flagged2 not inspected
  • 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

    warn15% of grade

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

    src/ai_objective_index/curated_validator.py: assigns a literal to token (BLOC…ID (len 23)) — non-provider secret literal; prefer environment intake. src/ai_objective_index/curated_validator.py: assigns a literal to token (BLOC…ME (len 18)) — non-provider secret literal; prefer environment intake. src/ai_objective_index/curated_validator.py: assigns a literal to token (BLOC…CE (len 24)) — non-provider secret literal; prefer environment intake. src/ai_objective_index/registry_intake/mcp_registry_evidence_gate.py: assigns a literal to token (BLOC…IM (len 28)) — non-provider secret literal; prefer environment intake. Reads secrets from the environment (e.g. src/ai_objective_index/github_staging.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 (src/ai_objective_index/aoi_030a2_build_verify.py: subprocess.* call; src/ai_objective_index/aoi_030a2_final_mcp_registry_reconcile.py: outbound HTTP/socket call). HIGH: shell/exec capability AND destructive filesystem writes together (src/ai_objective_index/aoi_030a2_build_verify.py: subprocess.* call; src/ai_objective_index/aoi_030a2_build_verify.py: destructive filesystem call (shutil.rmtree/os.remove/etc.)). discloses shell/exec capability: src/ai_objective_index/aoi_030a2_build_verify.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/aoi_030a2_final_common.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/aoi_030a2_final_mcp_registry_gate.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/aoi_030a2_final_mcp_registry_publish.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/aoi_030a2_final_pypi_upload_runner.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/aoi_030a2_final_pypi_verify.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/aoi_030a2_pypi_upload_gate.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/aoi_030a2_pypi_verify.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/aoi_mcp_registry_recovery_gate.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/aoi_mcp_registry_recovery_publish.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/deployment_push_sync.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/dist_build_runner.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/final_public_dry_run.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/github_issue_labels.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/github_post_upload_qa.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/github_release_manager.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/github_staging.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/hf_auth_check.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/local_build_tools.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/local_install_smoke.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/mcp_publisher_auth_check.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/mcp_publisher_installer.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/mcp_publisher_setup.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/mcp_registry_publish_diagnostics.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/mcp_registry_publish_runner.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/mcp_registry_submission_gate.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/mcp_registry_submit_execute.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/prepublic_sync.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/private_deployment_qa.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/public_launch_execute.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/public_metrics_snapshot.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/public_visibility_switch.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/pypi_publish_readiness.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/real_pypi_install_verify.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/real_pypi_upload_gate.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/real_pypi_upload_runner.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/residual_worktree_review.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/roe_source_intake_audit.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/tech_protection_audit.py: subprocess.* call discloses shell/exec capability: src/ai_objective_index/worktree_hygiene_audit.py: subprocess.* call discloses dynamic code execution: src/ai_objective_index/real_pypi_upload_gate.py: uses eval/exec/__import__ discloses broad/destructive filesystem access: src/ai_objective_index/aoi_030a2_build_verify.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/ai_objective_index/aoi_030a2_pypi_verify.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/ai_objective_index/hf_upload_packager.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/ai_objective_index/local_install_smoke.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/ai_objective_index/real_pypi_install_verify.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/ai_objective_index/release_archive_builder.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

    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 io.github.Isometric-Architect/[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

    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

Version history

Each release plotted by grade against the safe line at B. A version that sinks below the line has lost its trusted standing — the shape of a rug-pull.

VersionPublishedGradeScoreInspectedChange
v0.3.0a2 · current2026-05-30 C72.54/6 · 65%