Skills/ClawHub/pg

pg@1.0.3

VERIFIED· install only

Publisher claims: "Tunes, designs, and operates PostgreSQL: slow queries, indexes, schemas, migrations, vacuum, locks, replication, backups. Use when writing Postgres SQL or psql, designing tables and indexes, reading an EXPLAIN plan, running DDL or a migration against a live table, or when a query suddenly got slow, a table keeps growing while rows stay flat, autovacuum cannot keep up, "too many clients already" appears, a replica lags, deadlocks and lock waits pile up, pg_wal fills the disk, or an upgrade, a restore, or a partitioning plan is on the table. Covers connection pooling and PgBouncer, full-text, trigram and pgvector search, JSONB, roles and row-level security, PITR, extensions, and managed Postgres (RDS, Aurora, Cloud SQL, Neon, Supabase). Not for cross-engine SQL portability or ORM-level modeling." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher ivangdavila · publishing for 275 daysInstalls 5,551Last detonated 4d ago
$clawhub install pg
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

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 2026-11-10 and scored it 87/100 (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
Process kill commandSKILL.md:188 · Process kill command — agent can terminate processes| `kill -9` on a stuck backend | The postmaster treats it as a crash and restarts the entire cluster into recovery | `pg_cancel_backend(pid)`, then `pg_terminate_backend(pid)` |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentmemory-template.md:23 · HTML comment carrying imperative instructions to the agentMigration tooling, run-DDL vs hand-back-SQL, plan detail wanted, review gatesFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈5,282 tok
1 file · 29 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.