SKILLEMALL.ai

DF claude-team

Orchestrate multiple Claude Code workers via iTerm2 using the claude-team MCP server. Spawn workers with git worktrees, assign beads issues, monitor progress, and coordinate parallel development work.

Not recommendedcritical or high security findings · low grade D
modbender/skill-library-mcp Agent Skills author: modbender MIT 2 files · 1 script body ≈ 3 227 tokens Open the sourcegithub.com analyzed 2 d ago

Orchestrate multiple Claude Code workers via iTerm2 using the claude-team MCP server.

As a process F 47/100 · Will not run — References files that are not bundled: assets/com.claude-team.plist.template

ProcedureTelegramAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
D
40/100
safety, quality, tests
Safety 60%
28
Quality 40%
59
Run on models
none yet
Process rating
F
47/100
Will not run
References files that are not bundled: assets/com.claude-team.plist.template
Tools and files w 18
0
Result and completion w 14
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 9

  • high Dangerous commands cmd-persistence assets/setup.sh:41
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$PLIST_DEST"
  • high Dangerous commands cmd-persistence SKILL.md:304
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/com.claude-team.plist
  • high Dangerous commands cmd-persistence SKILL.md:328
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl bootstrap gui/$UID ~/Library/LaunchAgents/com.claude-team.plist
Medium and low: 6
  • medium Dangerous commands cmd-persistence assets/setup.sh:30
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST_DEST="$HOME/Library/LaunchAgents/com.claude-team.plist"
    code literal
  • medium Dangerous commands cmd-persistence SKILL.md:295
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    4. Installs it to `~/Library/LaunchAgents/com.claude-team.plist`
    quoted
  • medium Exfiltration net-credential-use SKILL.md:406
    Credential used in a network call (verify the destination is the intended service)
    curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendMessage" \
  • low Dangerous commands cmd-pipe-to-shell-known-host assets/setup.sh:13
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    echo "Error: uvx not found. Install uv with: curl -LsSf https://astral.sh/uv/install.sh | sh"
    code literal
  • low Exfiltration exfil-webhook-url SKILL.md:406
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendMessage" \
    placeholder
  • low Dangerous commands cmd-cron-mention SKILL.md:426
    Mentions editing / listing crontab (quoted — discussed, not commanded)
    Add to crontab (`crontab -e`):
    quoted

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: assets/com.claude-team.plist.template
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 47/100

Will not run. References files that are not bundled: assets/com.claude-team.plist.template
  • 0Tools and files. 1 referenced file(s) missing: assets/com.claude-team.plist.template
  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 12 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 39 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3227 tokens
  • 100Progress reporting. Reports progress
  • low 12 top-level sections: this looks like several domains in one skill
  • high The skill tells the model to perform an irreversible action with no human approval

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 200: enough signal without eating the budget
  • +4Structure: 35 headings
  • +3Step-by-step instructions: 39 items
  • +4Has examples (24 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.