MCP server · trust report

io.github.IgorGanapolsky/thumbgate

2 checks that ran failed — permission scope and transport config — so this release can’t be trusted as-is.

Publisher
io.github.IgorGanapolsky
Repository
github.com/IgorGanapolsky/ThumbGate
Install
npm:thumbgate, npm:thumbgate, npm:thumbgate, npm:thumbgate
Versions
4
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 checks0 clean4 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

    warn25% of grade

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

    install hook "postinstall" present and not a recognized benign build command; install hook "prepare" present and not a recognized benign build command; dependency "@google/genai" is edit-distance 2 from popular package "openai" (typosquat candidate)

  • Credential hygiene

    warn15% of grade

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

    .env.example: contains a hardcoded GitHub fine-grained PAT (gith…nt (len 47)) — in an example/sample file; verify it is not a real key. Reads secrets from the environment (e.g. scripts/activation-tracker.js) — the recommended intake shape.

  • Permission scope

    fail15% of grade

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

    HIGH: scripts/auto-wire-hooks.js: references a sensitive credential path (/mcp.json) — the tool-poisoning exfiltration target. HIGH: scripts/secret-scanner.js: references a sensitive credential path (id_rsa) — the tool-poisoning exfiltration target. HIGH: src/api/server.js: references a sensitive credential path (/mcp.json) — the tool-poisoning exfiltration target. HIGH: shell/exec capability AND network egress together — download-and-execute risk (scripts/agentic-data-pipeline.js: imports child_process and calls exec/spawn; scripts/billing.js: outbound HTTP/socket call). HIGH: shell/exec capability AND destructive filesystem writes together (scripts/agentic-data-pipeline.js: imports child_process and calls exec/spawn; scripts/activation-tracker.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename)). discloses shell/exec capability: scripts/agentic-data-pipeline.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/async-job-runner.js: imports child_process and calls exec/spawn discloses shell/exec capability: bin/cli.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/codegraph-context.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/contextfs.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/gates-engine.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/internal-agent-bootstrap.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/mcp-config.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/memory-firewall.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/operational-integrity.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/pr-manager.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/published-cli.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/secret-scanner.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/security-scanner.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/self-heal.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/self-healing-check.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/statusline-context.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/statusline-links.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/upstream-contribution-engine.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/workflow-sentinel.js: imports child_process and calls exec/spawn discloses shell/exec capability: scripts/workspace-evolver.js: imports child_process and calls exec/spawn discloses broad/destructive filesystem access: scripts/activation-tracker.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/agentic-data-pipeline.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/async-job-runner.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/audit-trail.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/auto-promote-gates.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/auto-wire-hooks.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/billing.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/build-metadata.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/chatgpt-ads-readiness-pack.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/claude-feedback-sync.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/cli-telemetry.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/cli-telemetry.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: bin/cli.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: bin/cli.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: scripts/context-engine.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/contextfs.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/dashboard.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/document-intake.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/evolution-state.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/experiment-tracker.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/explore.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: scripts/export-databricks-bundle.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/export-dpo-pairs.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/export-hf-dataset.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/feedback-loop.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/feedback-paths.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/feedback-to-rules.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/fs-utils.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/gates-engine.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/hook-thumbgate-cache-updater.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/hybrid-feedback-context.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: src/index.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: scripts/install-mcp.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/intervention-policy.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/jsonl-watcher.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/lesson-inference.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/lesson-synthesis.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/local-model-profile.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/meta-agent-loop.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/obsidian-export.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/oss-pr-opportunity-scout.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: bin/postinstall.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: scripts/pro-local-dashboard.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/proactive-agent-eval-guardrails.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/prompt-eval.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/published-cli.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/rate-limiter.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/reward-hacking-guardrails.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/risk-scorer.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/self-healing-check.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/seo-gsd.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: adapters/mcp/server-stdio.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: adapters/mcp/server-stdio.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/api/server.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: src/api/server.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: scripts/skill-generator.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/statusline-context.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/statusline-links.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/thompson-sampling.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/thumbgate-bench.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/upstream-contribution-engine.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/user-profile.js: destructive/writing fs.* call (write/unlink/rm/chmod/rename) discloses broad/destructive filesystem access: scripts/statusline.sh: 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 io.github.IgorGanapolsky/[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

    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); sends telemetry to third-party SDK (PostHog) — disclosure, verify opt-in; manifest/source references analytics 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
v1.27.17 · current2026-07-01 D554/6 · 65%