Taskhub MCP Server
taskhub-mcp
npm
v1.1.0
Published by jose890823 — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 9.3 = 91. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Forced-sequencing directive MTC-INJ-SEQ-1 | injection |
| −1.8 | Authority framing in tool metadata ×2 MTC-INJ-AUTH-1 | injection |
| −1.2 | Excessive ALL-CAPS emphasis in metadata MTC-INJ-CAPS | injection |
2. Client adoption risk — 91 − 1 = 90. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| ✓ | capability blast radius (minimal) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
| ✓ | inspection depth (source) — how much of the target the scan could see |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 4
medium Forced-sequencing directive (line jumping)MTC-INJ-SEQ-1
Forced-sequencing directive (line jumping) detected in the description of tool "taskhub_login". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.
Evidence: before using other tool
Fix: Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.
Location: tool taskhub_login · description
low Authority framing in tool metadataMTC-INJ-AUTH-1
Authority framing in tool metadata detected in the description of tool "taskhub_statuses". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.
Evidence: IMPORTANT
Fix: Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.
Location: tool taskhub_statuses · description
low Authority framing in tool metadataMTC-INJ-AUTH-1
Authority framing in tool metadata detected in the description of tool "taskhub_task_delete". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.
Evidence: IMPORTANT
Fix: Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.
Location: tool taskhub_task_delete · description
low Excessive ALL-CAPS emphasis in metadataMTC-INJ-CAPS
A run of shouted words is a common way to give injected instructions false authority.
Evidence: Search any entity by its systemCode (e.g. TSK-260218-A3K7, ORG-260218-B2C3, PRJ-260218-D4F1). Returns the entity type an
Location: tool taskhub_search · description
What this scan could not see
- Tools were statically extracted from the published source (29 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v1.1.0 latest |
A 90/100 | 4 | 1.7.0 | 2026-07-23 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan taskhub-mcp --onlineMore in Productivity & Workflow
Security scan results for the Agentchat MCP server.
Security scan results for the Alltrails MCP server.
Security scan results for the Anki MCP server.
Security scan results for the Apple Notes Ts MCP server.
Security scan results for the Bullet MCP server.
Security scan results for the Canny MCP server.