BC sandbox-npm-install
Install npm packages in a Docker sandbox environment. Use this skill whenever you need to install, reinstall, or update node_modules inside a container where the workspace is mounted via virtiofs. Native binaries (esbuild, lightningcss, rollup) crash on virtiofs, so packages must be installed on the local ext4 filesystem and symlinked back.
Install npm packages in a Docker sandbox environment.
As a process C 63/100 · Has gaps — weak spots: result and completion, progress reporting
The same skill appears in 1 more place: RA-Skills
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 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.
- 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 · 2
-
high Exfiltration
exfil-read-secret-filesscripts/install.sh:107Reads credential / secret filescp "$WORKSPACE_CLIENT/.npmrc" "$DEPS_DIR/"
Medium and low: 1
-
medium Exfiltration
exfil-read-secret-filesscripts/install.sh:104Reads credential / secret files (code comment)# Copy .npmrc if present (needed for private registries / scoped packages)
comment
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 17 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 853 tokens
- 100Running it twice. No mutating operations
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
- +1No license
- +2Single-language instructions
- +3Description length 342: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.