Ebm Calculator

Evidence-Based Medicine calculator for sensitivity, specificity, PPV, NPV, NNT, and likelihood ratios. Essential for clinical decision making and biostatisti...

Security Scan

The package implements an EBM calculator in a local Python script and asks for no credentials, but there are small documentation/code mismatches and an unvalidated output path that could lead to accidental file overwrite or unexpected file writes.

Purpose & Capability

The code (scripts/main.py) implements sensitivity, specificity, PPV/NPV, likelihood ratios, NNT, and pre/post-test conversion as advertised. No unrelated binaries, credentials, or network access are requested.

Instruction Scope

SKILL.md describes file I/O and 'Read input files, write output files' in risk table, but the script accepts inputs via CLI args and only writes output if --output is provided. The documentation implies more file input behavior than the code actually performs.

Install Mechanism

Instruction-only plus one included Python script; there is no install spec, no external downloads, and no packages required beyond the standard library.

Credentials

No environment variables, credentials, or config paths are requested. The tool operates purely on provided CLI parameters.

Persistence & Privilege

Skill is not forced-always, and does not attempt to modify other skills or system-wide settings. It has normal, limited presence.

What to consider before installing

This skill appears to do what it says and uses only standard Python libraries, but review before running: (1) The script will write to whatever path you pass to --output without validating it—don’t point it at sensitive files or system paths and avoid running as a privileged user; (2) The SKILL.md mentions reading input files but the script takes CLI arguments, so confirm how you intend to supply data; (3) Test the calculations with known examples before using results clinically (NNT rounding/interpretation is simplistic); and (4) Run the script in a sandbox or isolated environment if you want extra safety. If you need automatic invocation by an agent, ensure the agent won’t supply untrusted paths for --output.

Evidence-Based Medicine diagnostic test calculator.

Features

• Sensitivity / Specificity calculation
• PPV / NPV with prevalence adjustment
• Likelihood ratios (LR+ / LR-)
• Number Needed to Treat (NNT)
• Pre/post-test probability conversion

Parameters

Parameter	Type	Default	Required	Description
--mode, -m	string	diagnostic	No	Calculation mode (diagnostic, nnt, probability)
--tp, --true-pos	int	-	*	True positives (diagnostic mode)
--fn, --false-neg	int	-	*	False negatives (diagnostic mode)
--tn, --true-neg	int	-	*	True negatives (diagnostic mode)
--fp, --false-pos	int	-	*	False positives (diagnostic mode)
--prevalence, -p	float	-	No	Disease prevalence 0-1 (diagnostic mode)
--control-rate	float	-	**	Control event rate 0-1 (nnt mode)
--experimental-rate	float	-	**	Experimental event rate 0-1 (nnt mode)
--pretest	float	-	***	Pre-test probability 0-1 (probability mode)
--lr	float	-	***	Likelihood ratio (probability mode)
--output, -o	string	stdout	No	Output file path

* Required for diagnostic mode
** Required for nnt mode
*** Required for probability mode

Output Format

{
  "sensitivity": "float",
  "specificity": "float",
  "ppv": "float",
  "npv": "float",
  "lr_positive": "float",
  "lr_negative": "float",
  "interpretation": "string"
}

Risk Assessment

Risk Indicator	Assessment	Level
Code Execution	Python/R scripts executed locally	Medium
Network Access	No external API calls	Low
File System Access	Read input files, write output files	Medium
Instruction Tampering	Standard prompt guidelines	Low
Data Exposure	Output files saved to workspace	Low

Security Checklist

• No hardcoded credentials or API keys
• No unauthorized file system access (../)
• Output does not expose sensitive information
• Prompt injection protections in place
• Input file paths validated (no ../ traversal)
• Output directory restricted to workspace
• Script execution in sandboxed environment
• Error messages sanitized (no stack traces exposed)
• Dependencies audited

Prerequisites

No additional Python packages required.

Evaluation Criteria

Success Metrics

• Successfully executes main functionality
• Output meets quality standards
• Handles edge cases gracefully
• Performance is acceptable

Test Cases

1. Basic Functionality: Standard input → Expected output
2. Edge Case: Invalid input → Graceful error handling
3. Performance: Large dataset → Acceptable processing time

Lifecycle Status

• Current Stage: Draft
• Next Review Date: 2026-03-06
• Known Issues: None
• Planned Improvements:
  • Performance optimization
  • Additional feature support