lab-unit-harmonization
v0.1.0Comprehensive clinical laboratory data harmonization for multi-source healthcare analytics. Convert between US conventional and SI units, standardize numeric...
⭐ 0· 22·0 current·0 all-time
by@wu-uk
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name, description, and provided reference material (ckd_lab_features.md) match: the skill documents unit conversions, parsing rules, and clinical ranges for CKD-related labs. It does not ask for unrelated credentials, binaries, or installs, which is proportionate to a documentation/instruction skill.
Instruction Scope
Most instructions stay on-topic (parsing numbers, handling European decimals, unit conversion using clinical ranges). However, Step 0 prescribes removing any row with any missing numeric value (keeping only fully complete records) — this is a heavy-handed data-loss strategy that is not justified for many real-world workflows. The range-based unit-detection approach and the parse_value implementation (e.g., indiscriminate comma→dot replacement) can misclassify or corrupt values (thousand separators vs decimal commas, borderline values falling within multiple plausible unit ranges). These are correctness/data-quality concerns rather than security issues, but they grant broad destructive power over datasets if followed without testing.
Install Mechanism
No install spec and no code files — instruction-only. That lowers the risk since nothing is downloaded or written by the skill itself.
Credentials
The skill declares no environment variables, credentials, or config paths and the instructions do not reference external secrets or service tokens. Nothing requested appears disproportionate to the stated purpose.
Persistence & Privilege
always is false and the skill does not request persistent agent-level privileges or attempt to modify other skills or system configuration. Autonomous invocation is allowed by default but is not combined with any other red flags.
Assessment
This skill is a coherent, instruction-only guide for harmonizing lab data and does not request credentials or install code. Before using it on real data: 1) Do NOT blindly drop all rows with any missing value — consider imputation, partial-panel strategies, or domain-specific rules. 2) Test the parse and conversion logic on representative samples (watch out for thousand separators vs European decimal commas). 3) Validate unit-detection on edge cases (some analytes have overlapping numeric ranges across units). 4) Confirm conversion factors in your clinical context and verify any computed clinical ranges. 5) If you will run these instructions on PHI, ensure the execution environment is compliant with your data-protection policies (HIPAA/GDPR) and that logging or outputs won’t leak patient data. If you want, I can point out specific lines in the SKILL.md to adapt (e.g., safer missing-data handling, more robust numeric parsing, and conservative unit-detection heuristics).Like a lobster shell, security has layers — review code before you run it.
latestvk9747j7bc8g2dhp98zd5n6znc184w7q0
License
MIT-0
Free to use, modify, and redistribute. No attribution required.