DC hummingbot-developer
Developer skill for running Hummingbot and Gateway from source, building wheel and Docker images, and testing against Hummingbot API running from source. Use this skill when a developer wants to build, run, or test Hummingbot components locally.
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions
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.
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.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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".
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
- 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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 8
-
high Dangerous commands
cmd-install-from-urlSKILL.md:388Installs a package from an untrusted URL / archivepip install dist/hummingbot-*.whl --force-reinstall --no-deps
-
high Dangerous commands
cmd-install-from-urlSKILL.md:607Installs a package from an untrusted URL / archiveconda run -n hummingbot-api pip install <HUMMINGBOT_DIR>/dist/hummingbot-*.whl --force-reinstall --no-deps
-
high Dangerous commands
cmd-install-from-urlSKILL.md:855Installs a package from an untrusted URL / archiveconda run -n hummingbot-api pip install dist/hummingbot-*.whl --force-reinstall --no-deps
Medium and low: 5
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostscripts/install_deps.sh:178Pipe-to-shell installer from a well-known host (still executes remote code)curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash
-
medium Dangerous commands
cmd-pipe-to-shellscripts/install_deps.sh:261Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -fsSL https://get.docker.com | sh
vendor-host -
medium Dangerous commands
cmd-shell-rcscripts/install_deps.sh:308Writes to a shell startup fileecho " Restart your terminal (or run: source ~/.zshrc) to apply PATH changes."
-
medium Exfiltration
net-credential-usescripts/verify_build.sh:262Credential used in a network call (verify the destination is the intended service)GW_STATUS=$(curl -s --max-time 5 -u "$API_USER:$API_PASS" "$API_URL/gateway/status" 2>/dev/null)
-
low Dangerous commands
cmd-background-processscripts/run_dev_stack.sh:97Starts a background / autostarted processnohup node dist/index.js --passphrase="$PASSPHRASE" --dev > "$GW_LOG" 2>&1 &
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5441 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "commands"
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 5441 tokens
- 100Steps. 38 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 19 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 245: enough signal without eating the budget
- +4Structure: 63 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (67 code blocks)
- +3All 11 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.