Agent skill · Audited from source

Evidence Auditor

skill · WILLOSCAR/research-units-pipeline-skillsLicence not declaredAudited 19 Oct 2026 · source 81994516a430

★ 513pushed 14 days ago

✓SAFEGrade B · 89/100 · 19 Oct 2026 · 8199451

513repo stars · whole WILLOSCAR/research-units-pipeline-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 81994516a430 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Use when `paper-review` needs a claim-by-claim evidence gap report grounded in an extracted claim ledger.

Ask an AI about this pageGChatGPT CClaude PPerplexity GeGemini XGrok

CoCopilot AIGoogle AI Mode

Cite

Cite this page

ModelsAtlas. “Evidence Auditor (WILLOSCAR/research-units-pipeline-skills)”. Retrieved 19 Oct 2026. https://modelsatlas.com/skills/willoscar/evidence-auditor

Trust audit

Audit 0.4.1 · source read 19 Oct 2026

Trust score89/100✓SAFE B

0 critical0 high1 medium1 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 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	WARN	2
`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, no license.

Findings (2)

MEDIUMInventory / provenanceinv.symlink · .claude/skills

F-13 Inventory / provenanceCWE-1104Layer L0

.claude/skills

Why: link not followed
Fix: —

LOWInventory / provenanceinv.no_license

F-13 Inventory / provenanceCWE-1104Layer L0

Why: no LICENSE file and no repo licence
Fix: add a licence

Audit 0.4.1 · source sha 81994516a430 · 19 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

PublisherWILLOSCAR GitHub userOwner of the repository this skill is read from
Source folderWILLOSCAR/research-units-pipeline-skills/.codex/skills/evidence-auditorThe exact folder we audited
LicenceNot declaredAs the repository states it
Commit pinned for this verdict81994516a430A new audit runs when the source changes
Repository statusNot archivedLast push 14 days ago
Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Use when `paper-review` needs a claim-by-claim evidence gap report grounded in an extracted claim ledger.

---
name: evidence-auditor
description: "Use when `paper-review` needs a claim-by-claim evidence gap report grounded in an extracted claim ledger."
---

# Evidence Auditor

## Triggers & routing

- **Trigger**: evidence audit, missing evidence, unsupported claims, 审稿证据审计, 证据缺口.
- **Use when**: `paper-review` 流程中,需要逐条检查 claim 的证据链、缺 baseline、评测薄弱点。
- **Skip if**: 缺少 claims 输入(例如还没有 `output/CLAIMS.md`)。
- **Network**: none.
- **Guardrail**: 只写“缺口/风险/下一步验证”,不要替作者补写论述或引入新主张。


Transforms a claim ledger into a gap report for `paper-review`.

## Input

- `output/CLAIMS.md`

## Output

- `output/MISSING_EVIDENCE.md`
- `output/EVIDENCE_AUDIT.jsonl` (`review-evidence-gap.v1`)

## Contract

Each gap block should include:
- claim reference
- what evidence is already present
- what is missing or weak
- minimal fix
- severity

Each JSONL record must retain `claim_id` and a stable `gap_id` so the final
review can cite the exact failure rather than paraphrasing an unlocated concern.

## Script boundary

`scripts/run.py` should:
- iterate existing claims only
- classify the likely evidence risk
- write actionable, bounded gap items

It should not invent new claims or rewrite the manuscript.

## Acceptance

- every claim has a corresponding evidence note or gap item
- minimal fixes are actionable and concrete
- structured records join back to every `claim_id`

## Non-goals

- manuscript rewriting
- novelty assessment
- recommendation writing

Excerpt, first 1,448 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 8199451

Download folder ↗

git clone https://github.com/WILLOSCAR/research-units-pipeline-skills
git -C research-units-pipeline-skills checkout 81994516a430

The author documents no install command, so this uses the repository directly. Our verdict covers commit 81994516a430 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

2026-10-19
✓SAFE B 89 / 100
first audit · source 81994516a430