Scienceworld Material ClassifierSAFE
Create, Evaluate, and Connect AI Skills
Overview
Create, Evaluate, and Connect AI Skills
4501e739125cOBSERVED · 2026-10-12What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: scienceworld-material-classifier description: This skill makes a determination about a material's property (e.g., conductivity) based on environmental cues or domain knowledge when direct testing fails. Trigger it when experimental actions are invalid or unavailable, requiring a logical inference. It uses observed object properties and common-sense reasoning to classify the material and decide its final disposition. --- # Material Classification Skill ## When to Use Activate when direct experimental testing of a material property (conductivity, magnetism, etc.) fails or equipment is unavailable, and you need to classify the material by inference to complete a sorting task. ## Procedure 1. `focus on <OBJECT>` — identify the target and note its material composition. 2. Attempt direct testing if equipment exists (e.g., `connect <OBJECT> terminal 1 to <WIRE> terminal 2`). 3. If testing fails, infer the property from the object's material. Consult `references/material_properties.md` for lookup. 4. `move <OBJECT> to <CONTAINER>` — place in the appropriate classification container. 5. `look at <CONTAINER>` — verify the object was placed correctly. ## Example **Task:** Classify a glass jar for electrical conductivity when the circuit test is unavailable. 1. `focus on glass jar` 2. `connect glass jar terminal 1 to yellow wire terminal 2` — action fails (invalid connection). 3. Inference: glass is an electrical insulator → non-conductive. 4. `move glass jar to orange box` 5. `look at orange box` — observation: "containing a glass jar" — classification complete.
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
4501e739125cfull audit observations/trust-audit/skill/zjunlp__scienceworld-material-classifier.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 4501e739125c | SAFE | B | 89 | first audit |
Questions
What does the Scienceworld Material Classifier skill do?
Create, Evaluate, and Connect AI Skills
Is Scienceworld Material Classifier safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Scienceworld Material Classifier access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (4501e739125c), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.