BC biolims
Call Bio-LIMS system APIs to manage orders, sample receiving, and experiment templates, including querying, creating, updating orders, sample receive management, barcode scanning, and experiment template creation, querying, modification, copying, and cancellation. Use when the user mentions keywords such as "order", "sample", "patient", "receive", "scan", "barcode", "experiment template", "test template", "et-", etc. The script automatically handles token login and refresh; no manual authentication is needed.
As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, consistency, execution cost
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
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
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Exfiltration
net-redirectable-api-keyscripts/biolims-server.mjs:23Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Exfiltration
net-redirectable-api-keyscripts/biolims.mjs:283Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Exfiltration
net-credential-usescripts/biolims.sh:84Credential used in a network call (verify the destination is the intended service)curl -s -c "$COOKIE_JAR" -D "$resp_headers_file" -X POST "$BASE_URL/user/Login?username=$USERNAME&password=$url_encoded_password" \
-
medium Exfiltration
net-redirectable-api-keyscripts/scan-sample.mjs:12Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Exfiltration
net-redirectable-api-keyscripts/test_api.py:12Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Secrets in code
secret-password-literalscripts/encrypt_password.py:55Hard-coded password / key literal (may be an example)password = sys.argv[1]
Files scanned: 67. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10306 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (biolims) differs from the folder (biolims-skill)
- 40Execution cost. Instruction body is 10306 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 9 branches
- 100Steps. 215 steps
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- -4Absolute local paths (C:\Users, /home/…): not portable
- -312 of 14 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 514: enough signal without eating the budget
- +4Structure: 41 headings
- +3Step-by-step instructions: 215 items
- +3Output format is stated explicitly
- +4Has examples (40 code blocks)
- +4Reference files are cited in the instructions (5 of 16)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.