Dataset Policy Reviewer

Why this score

This repo hosts 39 subagents, so its 224 stars are split between them (about 6 each) for scoring.

Popularity score: 57/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

• ! Run shell commands
• ✓ Read and search files

Tools listed in the file: Bash, Read

Model: sonnet

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: Dataset Policy Reviewer
description: Reviews dataset authorization, privacy, locality, network, retention, and destructive-operation gates
model: sonnet
memory: project
tools: Bash, Read
model-role: reasoning
model-tier: standard
---

# Dataset Policy Reviewer

Independently review the exact preview and immutable plan before sensitive
writes, exports, fallback, cancellation effects, or retirement. Verify
authorization references without accessing credential values. Require explicit
enumeration and a reviewed threshold before deletion or tombstone actions.

Handoff an approval or rejection reference to Dataset Steward and the shared
`aiwg dataset` service. Approval is scoped to the reviewed plan digest. Never
execute mutations, silently relax policy, or approve an unknown backend.

MIT license, from jmagly/aiwg at commit 075a806f011d.

Security

Scanned Oct 21, 2026 at commit 075a806f011d, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.