Agent skill · Audited from source
tooluniverse-drug-drug-interaction
skill · mims-harvard/tooluniverseApache-2.0 licenceAudited 14 Nov 2026 · source 48a20ff67149
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 48a20ff67149 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Assess drug-drug interactions — CYP metabolic interactions (substrate/inhibitor/inducer), transporter (P-gp, BCRP, OATP) effects, pharmacodynamic synergy/antagonism, clinical significance scoring, and management…
Cite
Cite this page
ModelsAtlas. “tooluniverse-drug-drug-interaction (mims-harvard/tooluniverse)”. Retrieved 14 Nov 2026. https://modelsatlas.com/skills/mims-harvard/tooluniverse-drug-drug-interaction
Trust audit
Audit 0.4.1 · source read 14 Nov 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 1 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | PASS | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (1)
Audit 0.4.1 · source sha 48a20ff67149 · 14 Nov 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publishermims-harvard GitHub organizationOwner of the repository this skill is read from
- Source foldermims-harvard/tooluniverse/skills/tooluniverse-drug-drug-interactionThe exact folder we audited
- LicenceApache-2.0As the repository states it
- Commit pinned for this verdict48a20ff67149A new audit runs when the source changes
- Repository statusNot archivedPushed today
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Assess drug-drug interactions — CYP metabolic interactions (substrate/inhibitor/inducer), transporter (P-gp, BCRP, OATP) effects, pharmacodynamic synergy/antagonism, clinical significance scoring, and management…
--- name: tooluniverse-drug-drug-interaction description: Assess drug-drug interactions — CYP metabolic interactions (substrate/inhibitor/inducer), transporter (P-gp, BCRP, OATP) effects, pharmacodynamic synergy/antagonism, clinical significance scoring, and management recommendations. Use for polypharmacy review, prescribing decision support, and safety analysis when adding or switching drugs. disable-model-invocation: true --- # Drug-Drug Interaction Prediction & Risk Assessment Systematic analysis of drug-drug interactions with evidence-based risk scoring, mechanism identification, and clinical management recommendations. **KEY PRINCIPLES**: 1. **Report-first approach** - Create DDI_risk_report.md FIRST, then populate progressively 2. **Bidirectional analysis** - Always analyze A→B and B→A interactions (effects may differ) 3. **Evidence grading** - Grade all DDI claims by evidence quality (★★★ FDA label, ★★☆ clinical study, ★☆☆ theoretical) 4. **Risk scoring** - Multi-dimensional scoring (0-100) combining mechanism + severity + clinical evidence 5. **Patient safety focus** - Provide actionable clinical guidance, not just theoretical interactions 6. **Mandatory completeness** - All analysis sections must exist with explicit "No interaction found" when appropriate --- ## LOCAL PHARMACOLOGY REFERENCE (USE FIRST) Before querying any external database, consult the local reference script for instant answers on CYP/UGT roles and known critical interactions: ``` scripts/pharmacology_ref.py (no external dependencies, runs offline) # Q927 pattern — valproate + lamotrigine: python scripts/pharmacology_ref.py --type interaction --drug1 "valproate" --drug2 "lamotrigine" # What does a drug do to UGT enzymes? python scripts/pharmacology_ref.py --type ugt_inhibitor --drug "valproate" # What enzymes metabolise a drug? python scripts/pharmacology_ref.py --type ugt_substrate --drug "lamotrigine" python scripts/pharmacology_ref.py --type cyp_substrate --drug "warfarin" # Which drugs inhibit / induce a specific CYP? python scripts/pharmacology_ref.py --type cyp_inhibitor --enzyme "CYP3A4" python scripts/pharmacology_ref.py --type cyp_inducer --enzyme "CYP2C9" # Narrow therapeutic index checklist: python scripts/pharmacology_ref.py --type narrow_ti # All known interactions for one drug: python scripts/pharmacology_ref.py --type all_interactions --drug "lamotrigine" ``` **Covered interactions include** (severity / mechanism): | Pair | Severity | Key mechanism | |------|----------|---------------| | valproate + lamotrigine | **Major** | UGT1A4 inhibition → 2× lamotrigine levels + SJS risk | | carbamazepine + lamotrigine | Major | UGT1A4 induction → 50% ↓ lamotrigine | | oral contraceptives + lamotrigine | Major | UGT1A4 induction → 50% ↓ lamotrigine | | valproate + phenytoin | Major | CYP2C9 inhibition + protein displacement | | carbamazepine + valproate | Moderate | Epoxide hydrolase inhibition → toxic metabolite ↑ | | simvastatin + ketoconazole | **Contraindicated** | CYP3A4 inhibition → rhabdomyolysis | | simvastatin + clarithromycin | Contraindicated | CYP3A4 inhibition → rhabdomyolysis | | rifampin + warfarin | Major | CYP2C9 induction → INR collapse | | amiodarone + warfarin | Major | CYP2C9 inhibition → INR rise | | clopidogrel + omeprazole | Moderate | CYP2C19 inhibition → reduced antiplatelet activation | | quinidine + digoxin | Major | P-gp inhibition → 2× digoxin levels | | lithium + NSAIDs | Major | Reduced renal clearance → lithium toxicity | | fluoxetine + MAOIs | Contraindicated | Serotonin syndrome | The script also covers UGT2B7 substrates (morphine, zidovudine) inhibited by valproate, UGT1A1 induction by rifampin, and the complete narrow therapeutic index list with monitoring parameters. ## LOOK UP, DON'T GUESS When uncertain about any scientific fact, SEARCH databases first (PubMed, UniProt, ChEMBL, ClinVar, etc.) rather than reasoning from memory. A database-verified answer is always more reliable than a guess. ## New Symptom After New Medication: First-Line Reasoning When a patient develops NEW symptoms after starting a new medication, the FIRST question is: could the new drug be interacting with an existing medication? Specifically check: (1) Does the new drug inhibit metabolism of an existing drug? (2) Does the new drug have additive pharmacodynamic effects? --- ## When to Use This Skill Apply when users: - Ask about interactions between 2+ specific drugs - Need polypharmacy risk assessment (5+ medications) - Request medication safety review for a patient - Ask "can I take drug X with drug Y?" - Need alternative drug recommendations to avoid DDIs - Want to understand DDI mechanisms - Need clinical management strategies for known interactions - Ask about QTc prolongation risk from multiple drugs --- ## Clinical Reasoning Framework Before querying any database, apply this reasoning framework to predict interactions mechanistically. ### The Perpetrator-Victim Model In every drug interaction, identify two roles: - **PERPETRATOR**: the drug causing the change (the inhibitor, inducer, or pharmacodynamic amplifier) - **VICTIM**: the drug being affected (the one whose levels or effects change) For each drug pair, ask these questions in order: 1. **Does the perpetrator change how the victim is absorbed, distributed, metabolized, or eliminated?** If yes, this is a pharmacokinetic interaction. Determine which enzyme or transporter is involved (CYP450, UGT, P-gp, OATP, etc.). 2. **Is the perpetrator an inhibitor or an inducer of that pathway?** - Inhibitor → victim levels go UP → predict increased efficacy or toxicity - Inducer → victim levels go DOWN → predict reduced efficacy or therapeutic failure 3. **What happens clinically when the victim's level changes?** Predict the downstream consequence: toxicity from supratherapeutic levels, or treatment failure from subtherapeutic levels. 4. **Always check the reverse direction.** Analyze B→A as well as A→B. The pe
Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 48a20ff
git clone https://github.com/mims-harvard/tooluniverse git -C tooluniverse checkout 48a20ff67149
The author documents no install command, so this uses the repository directly. Our verdict covers commit 48a20ff67149 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
48a20ff67149
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/mims-harvard/tooluniverse-drug-drug-interaction/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
mims-harvard/tooluniverse
Generate comprehensive disease research reports covering genetics (causal genes, GWAS, OMIM), pathways (Reactome, KEGG), drugs (existing therapies, repurposing candidates), clinical trials, epidemiology (prevalence,…
mims-harvard/tooluniverse
Analyze CRISPR-Cas9 genetic screens — MAGeCK gene-level scores, sgRNA count QC, replicate correlation, hit prioritization, and pathway GSEA on screen output. Use for genome-wide essentiality screens, synthetic-lethality…
mims-harvard/tooluniverse
Strategic clinical trial design feasibility assessment. Analyzes 6 dimensions (endpoint, population, comparator, effect size, duration, regulatory pathway) using precedent trials and FDA guidance. Produces enrollment…
mims-harvard/tooluniverse
AI-driven patient-to-trial matching for precision oncology and rare-disease care. Transforms a patient's molecular profile (mutations, biomarkers, expression) and clinical state into ranked clinical-trial…
mims-harvard/tooluniverse
Chemical safety and toxicology assessment integrating ADMET-AI predictions, CTD toxicogenomics, PubChemTox experimental data, GHS/IARC hazard classification, and exposure-context analysis. Use for chemical hazard…
mims-harvard/tooluniverse
Search and retrieve clinical practice guidelines from 12+ authoritative sources — NICE, WHO, NCCN, AHA, ADA, SIGN, USPSTF, IDSA, NIH consensus, ESMO/ESC/EASL European societies, and US specialty associations. Use for…
Add this badge to your README
[](https://modelsatlas.com/skills/mims-harvard/tooluniverse-drug-drug-interaction/)
<a href="https://modelsatlas.com/skills/mims-harvard/tooluniverse-drug-drug-interaction/"><img src="https://modelsatlas.com/skills/mims-harvard/tooluniverse-drug-drug-interaction/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about tooluniverse-drug-drug-interaction
What does the tooluniverse-drug-drug-interaction skill do?
Is tooluniverse-drug-drug-interaction safe to install?
What can tooluniverse-drug-drug-interaction access on my machine?
How current is this page?
Sources
- github.com/mims-harvard/tooluniverse/tree/main/skills/tooluniver — the audited source at commit 48a20ff67149 and every finding aboveObserved · 14 Nov 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the tooluniverse-drug-drug-interaction skill do?
- Is tooluniverse-drug-drug-interaction safe to install?
- What can tooluniverse-drug-drug-interaction access on my machine?