Skills/Docker MCP Catalog/task-orchestrator

task-orchestrator@r10

CAUTION· install only

Publisher claims: "Model Context Protocol (MCP) server for comprehensive task and feature management, providing AI assistants with a structured, context-efficient way to interact with project data." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Docker MCP CatalogPublisher jpicklyk · publishing for 19 daysInstalls 0Last detonated 4d ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
ANTHROPIC_API_KEYConfiguration, not credentials: CLAUDE_BIN, GITHUB_ACTIONS
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard. It asks for ANTHROPIC_API_KEY and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --net declared -- docker run -i --rm mcp/task-orchestrator

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is task-orchestrator@r10 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-10 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; Instructs the agent to modify its persistent memory or instruction files; Instructs the agent to modify its persistent memory or instruction files. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionclaude-plugins/task-orchestrator/skills/run-wave/SKILL.md:190 · File type combined with upload action — agent may exfiltrate local data files…` segment | | 3 Plan | `node "<helper>" plan --in <scratchpad>/run-wave/snapshot.json --scratchpad <scratchpad>` (add `--method B` whenever F1 selected Method B, so `meta.method` is `"B"`; without `--method`, the plan may still pick B when…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification command.claude/commands/deploy_to_docker.md:200 · File permission modification command — agent changes file ownership/permissions- **DB permission errors:** `docker run --rm -v mcp-task-data:/app/data --user root amazoncorretto:25-al2023-headless chown -R 1001:1001 /app/data`.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionclaude-plugins/task-orchestrator/skills/run-wave/SKILL.md:193 · File type combined with upload action — agent may exfiltrate local data files…der `node "<helper>" run-ops --plan <plan> --phase adopt-notes --notes <observed.json>` and send each op as its own `notes_write` call under its `tokenFiles` entry (none when null), reading each element. A version_conflict on a delete mean…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
CRITICAL
HTML comment carrying imperative instructions to the agentclaude-plugins/task-orchestrator/skills/model-effort/SKILL.md:12 · HTML comment carrying imperative instructions to the agentBEGIN GENERATED:dispatch-policy (do not edit; run _fragments/generate.mjs)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File type combined with upload actionclaude-plugins/task-orchestrator/skills/run-wave/SKILL.md:177 · File type combined with upload action — agent may exfiltrate local data files`state.json`. On the task notification the director sends the result JSON verbatim and the usageFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Instructs the agent to modify its persistent memory or instruction files.claude/skills/prepare-release/SKILL.md:255 · Instructs the agent to modify its persistent memory or instruction filesAlso update the version table in `claude-plugins/CLAUDE.md`: find the row for each bumped plugin andFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actioncurrent/src/test/resources/golden/a1-seatless/README.md:55 · File type combined with upload action — agent may exfiltrate local data files- `rest_advance_422_feature_task.json` — `POST /api/v1/items/{feature-task id}/advance` withFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Instructs the agent to modify its persistent memory or instruction files.claude/skills/plugin-impact-review/SKILL.md:59 · Instructs the agent to modify its persistent memory or instruction files…nts)? The cache is version-keyed and re-extracts lazily, so a plain marketplace update does not pick it up: run the forced refresh in `claude-plugins/CLAUDE.md` (rm -rf the cache, then marketplace update) - [ ] Is the orchestration-context…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
MCP server using network transport (SSE/HTTP)claude-plugins/task-orchestrator/skills/init/SKILL.md:47 · MCP server using network transport (SSE/HTTP) — data sent over network…te the orchestration entry the way `hooks/session-start.mjs` does: `.mcp.json` `mcpServers`, then `~/.claude.json` `mcpServers` and `projects[<dir>].mcpServers`; an entry counts when its key contains `task-orchestrator`. An HTTP entry carr…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File type combined with upload actionclaude-plugins/task-orchestrator/skills/configure-server/SKILL.md:328 · File type combined with upload action — agent may exfiltrate local data files… every session, subagent and headless `/ralph` iteration that reads `<main>/.mcp.json` with the variables set, and nothing in the plugin stops a non-director agent from calling the director entry. So a separate director token separates ide…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Auto-update or dynamic fetch configuration.claude/skills/spec-quality/SKILL.md:197 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeserver restart, config hot-reload); resume after compaction or `--resume`. An item may addFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionclaude-plugins/task-orchestrator/skills/run-wave/SKILL.md:192 · File type combined with upload action — agent may exfiltrate local data files… | | 5 Open | `node "<helper>" run-ops --plan <scratchpad>/run-wave/<runId>/plan.json --phase open` renders `{tool: "runs_write", ops: [{op: "open", rootId, items, scopeId?, label: <runId>, title, hints: {plan, method, worktreeMode}, budge…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandscripts/ci/smoke-test-image.sh:111 · File permission modification command — agent changes file ownership/permissionssh -c 'cp /seed.sqlite /app/data/current-tasks.db && chown 1001:1001 /app/data/current-tasks.db'Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actioncurrent/src/test/resources/golden/a1-seatless/README.md:14 · File type combined with upload action — agent may exfiltrate local data files> `{success, data}`) and the two `rest_gate_*.json` captures are `rest_context_*.json` (`POST /api/v1/ops/items_read`,Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionclaude-plugins/task-orchestrator/skills/orchestrate/SKILL.md:97 · File type combined with upload action — agent may exfiltrate local data files…`/task-orchestrator:run-wave` reads the project's `.taskorchestrator/run-profile.json`, and a project dispatch contract pins its own build self-check. A seat you dispatch **by hand**, outside both of those, gets neither unless you put it t…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandclaude-plugins/task-orchestrator/skills/configure-server/SKILL.md:18 · Process kill command — agent can terminate processes(env, default true) disables resource-lease gate enforcement server-wide — a kill switch for leaseFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈148,350 tok
31 files · 80 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim jpicklyk: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
Publish a new version to Docker MCP Catalog, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jpicklykPropose a patch to the maintainer