Skills/Glama/dbshield

dbshield@0.2.1

VERIFIED· install only

Publisher claims: "Enables AI coding agents to safely inspect and mutate relational databases through AST-level SQL guardrails, isolated dry-run rollback previews, automatic PII masking, and virtual schema hiding. Sensitive mutations are gated behind human sign-off via Slack, Microsoft Teams, or a live web approval feed." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher ritualdev-lab · publishing for 31 daysInstalls 0Last detonated 6d ago
$npx skills add dbshield
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
DATABASE_URLDBSHIELD_AUDIT_SECRETConfiguration, not credentials: DBSHIELD_AIR_GAPPED, DBSHIELD_ALLOW_DESTRUCTIVE_DDL, DBSHIELD_BLOCK_UNINDEXED_SEQ_SCAN, DBSHIELD_DIALECT, DBSHIELD_DISALLOW_BREAKING_RENAMES, DBSHIELD_ENABLE_COST_GATE, DBSHIELD_ENABLE_METRICS, DBSHIELD_ENABLE_MIGRATION_GATE, DBSHIELD_ENABLE_PII_MASKING, DBSHIELD_ENABLE_SEMANTIC_GUARD, DBSHIELD_ENFORCE_CONCURRENT_INDEX, DBSHIELD_MAX_ESTIMATED_COST, DBSHIELD_MAX_ESTIMATED_ROWS, DBSHIELD_MAX_MUTATION_ROWS, DBSHIELD_MAX_READ_ROWS, DBSHIELD_METRICS_HOST, DBSHIELD_METRICS_PORT, DBSHIELD_PROXY_HOST, DBSHIELD_PROXY_PORT, DBSHIELD_REQUIRE_INTENT_FOR_SENSITIVE, DBSHIELD_SAFETY_TIER, DBSHIELD_STATEMENT_TIMEOUT_MS, DBSHIELD_STORAGE_PATH, DBSHIELD_UPSTREAM_HOST, DBSHIELD_UPSTREAM_PORT, DBSHIELD_WARN_ESTIMATED_COST, DBSHIELD_WARN_ESTIMATED_ROWS, RITUAL_AIR_GAPPED
Where it talks to
ritualdev.in (its own)Also microsoftonline.com, adaptivecards.io, slack.com, google.com, okta.com, pingone.com, enterprise.local, shields.io, githubusercontent.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names microsoftonline.com, adaptivecards.io, slack.com, google.com, okta.com, pingone.com, enterprise.local, shields.io, githubusercontent.com as well as its own vendor. The guard injects DATABASE_URL, DBSHIELD_AUDIT_SECRET only into requests to ritualdev.in (and its subdomains) and refuses the rest.

$vet-skills run --secrets DATABASE_URL=ritualdev.in,DBSHIELD_AUDIT_SECRET=ritualdev.in -- <the server's command>

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-08 and scored it 84/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionsrc/cli.ts:234 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` Throughput: ${qps.toLocaleString()} queries/sec`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageSKILL.md:50 · npx invocation of non-well-known package — may execute untrusted codenpx @ritualdev-lab/dbshield dashboard --port 3100Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:53 · npx invocation of non-well-known package — may execute untrusted codenpx @ritualdev-lab/dbshield report --compliance soc2 --audit-pdf audit.pdfFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:47 · npx invocation of non-well-known package — may execute untrusted codenpx @ritualdev-lab/dbshield proxy --port 5433Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Credential pass-through configurationsrc/sandbox/sqlite-vfs-shim.ts:29 · Credential pass-through configuration — agent relays sensitive credentials* Explicit bypass token for DBShield maintenance/vacuum operations.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
npx invocation of non-well-known packageSKILL.md:56 · npx invocation of non-well-known package — may execute untrusted codenpx @ritualdev-lab/dbshield install-claudeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:44 · npx invocation of non-well-known package — may execute untrusted codenpx @ritualdev-lab/dbshield startFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈713 tok
1 file · 80 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.