Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Database Migration

skill · agulli/atlas-agentsLicence not declaredAudited 18 Oct 2026 · source dd4da722e22a

★ 583pushed 93 days ago
✓SAFEGrade B · 89/100 · 18 Oct 2026 · dd4da72
583repo stars · whole agulli/atlas-agents

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit dd4da722e22a and found no filesystem, network or shell access and no hard-coded secrets. What it does: Safely run database schema migrations. Use when asked to update database schema, add columns, create tables, run alembic, or apply Django migrations.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Database Migration (agulli/atlas-agents)”. Retrieved 18 Oct 2026. https://modelsatlas.com/skills/agulli/database-migration

2 skills are called “Database Migration”. You are viewing agulli/atlas-agents.

Trust audit

Audit 0.4.1 · source read 18 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium2 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

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS1
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS1
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass, no license.

Findings (2)

LOWInventory / provenanceinv.no_license
F-13 Inventory / provenanceCWE-1104Layer L0
Why
no LICENSE file and no repo licence
Fix
add a licence
LOWPrompt injectionreview.instruction_override · SKILL.md
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
"The command succeeded" is NOT accepted as sufficient evidence
Why
The skill instructs the agent to override a common, successful-outcome signal in favor of its own verification procedure.
Fix
rewrite it so the instruction says plainly what it does, and asks the user before it acts

Audit 0.4.1 · source sha dd4da722e22a · 18 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisheragulli GitHub userOwner of the repository this skill is read from
  • Source folderagulli/atlas-agents/ch09_agent_skills/skills/database-migrationThe exact folder we audited
  • LicenceNot declaredAs the repository states it
  • Commit pinned for this verdictdd4da722e22aA new audit runs when the source changes
  • Repository statusNot archivedLast push 93 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Safely run database schema migrations. Use when asked to update database schema, add columns, create tables, run alembic, or apply Django migrations.

---
name: database-migration
description: Safely run database schema migrations. Use when asked to update database schema, add columns, create tables, run alembic, or apply Django migrations.
license: MIT
compatibility: Requires python 3.10+ and one of alembic, django, or prisma
---

## Clarification Gates

Before executing any migration, you must have clear answers to all of the following. If any is missing or ambiguous, STOP and ask. Do not infer from filenames, branch names, or previous conversation context.

- **Environment:** local / staging / production?
- **Backup confirmed:** Has a database backup been taken in the last 24 hours?
- **Migration scope:** Is this a new column/table, or does it modify/drop existing data?

An agent that guesses the environment and gets it wrong has just migrated the wrong database. Ask first.

## Process

1. **Identify the migration tool.** Check the project for:
   - `alembic.ini` → Alembic (SQLAlchemy)
   - `manage.py` → Django migrations
   - `prisma/schema.prisma` → Prisma
   If none are found, ask the user which tool to use. Do not guess.

2. **Generate the migration.**
   - Alembic: `alembic revision --autogenerate -m "description"`
   - Django: `python manage.py makemigrations`
   - Prisma: `npx prisma migrate dev --name description`

3. **Review the generated migration file.** Read the entire file. Check for:
   - Columns being dropped (STOP and ask the user)
   - Table renames (STOP and ask the user)
   - Non-nullable columns added without defaults (this will fail on non-empty tables)

4. **Dry run.** If the tool supports it:
   - Alembic: `alembic upgrade head --sql` (generates SQL without executing)
   - Django: `python manage.py sqlmigrate <app> <migration_number>`

5. **Apply the migration** only after reviewing the dry run output.

6. **Verify.** Query the database schema directly to confirm the change took effect:
   ```sql
   -- PostgreSQL
   SELECT column_name, data_type FROM information_schema.columns WHERE table_name = 'target_table';
   -- SQLite
   PRAGMA table_info(target_table);
   ```

## Rationalizations

| Excuse | Rebuttal |
|--------|----------|
| "It's just an ADD COLUMN, I'll skip the review" | Schema locks can occur even on simple additions. Always review. |
| "The autogenerated migration looks correct" | Autogenerate guesses. It sometimes generates DROP + CREATE instead of ALTER. Read the file. |
| "I'll just run it — we can roll back" | Not all migrations are reversible. Dropping a column destroys data permanently. |

## Verification

- [ ] Migration file was read in full before applying
- [ ] No columns were dropped without explicit user approval
- [ ] Database schema was queried after migration to confirm the change
- [ ] "The command succeeded" is NOT accepted as sufficient evidence

Excerpt, first 2,804 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 dd4da72

Download folder ↗
git clone https://github.com/agulli/atlas-agents
git -C atlas-agents checkout dd4da722e22a

The author documents no install command, so this uses the repository directly. Our verdict covers commit dd4da722e22a 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

  1. ✓SAFE B 89 / 100

    first audit · source dd4da722e22a

Questions about Database Migration

Is Database Migration 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 Database Migration 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 (dd4da722e22a), read on 2026-10-18. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

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.