BA referral-letter-generator
Generate medical referral letters with patient summary, reason for referral.
As a process A 84/100 · Runs to the end — no weak spots found
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 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.
How to improve
- 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
✓ No critical or high findings
Medium and low: 2
-
medium Dangerous commands
cmd-eval-dynamicscripts/main.py:355Dynamic code execution from decoded/untrusted inputos.system(f"{sys.executable} -m pip install reportlab -q") -
medium Dangerous commands
cmd-eval-dynamicscripts/main.py:473Dynamic code execution from decoded/untrusted inputos.system(f"{sys.executable} -m pip install python-docx -q")
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "skill-author"
Process rating: all ten parameters 84/100
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 92 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2373 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 26 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 76: 120–800 characters recommended
- -45 reference files, but SKILL.md never points to them: the model will not open them
- +2Single-language instructions
- +4Structure: 31 headings
- +3Step-by-step instructions: 92 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.