BC nhtsa-vehicle
Synthesized reference notes from three US Government vehicle-safety sources: NHTSA Cybersecurity Best Practices for the Safety of Modern Vehicles (updated 2022, final), NHTSA Automated Driving Systems 2.0: A Vision for Safety (2017), and a 16-section selection of 49 CFR Part 571 (FMVSS) pinned at eCFR versioner date 2025-01-01. Use for voluntary vehicle cybersecurity practices, the ADS 2.0 twelve priority safety design elements, and FMVSS occupant protection, brakes/stability/lighting, and fuel/EV integrity requirements. Not ISO 26262, not ASPICE, not ISO/SAE 21434, not UNECE R155/R156, not SAE J3016, and not the full Part 571; the FMVSS material is a selection of vehicle-level minimum performance standards, not a process standard.
Synthesized reference notes from three US Government vehicle-safety sources: NHTSA Cybersecurity Best Practices for the Safety of Modern Vehicles (updated…
As a process C 63/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securitychapters/ch02-nhtsa-cyber-practices.md:37Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Cybersecurity testing and vulnerability identification.** Evaluate off-the-shelf and open-source components against known vulnerabilities; run product cybersecurity testing (including penetration
Files scanned: 9. 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 45 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2234 tokens
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
- +4No input/output examples
- +2Single-language instructions
- +3Description length 741: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 45 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.