Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add UnboundCompute/security-agent-skills --skill hunting-connection-string-and-jdbc-url-injectiongit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-connection-string-and-jdbc-url-injection)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-connection-string-and-jdbc-url-injection"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-connection-string-and-jdbc-url-injection/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-connection-string-and-jdbc-url-injection"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-connection-string-and-jdbc-url-injection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00166 | $0.01996 |
| Opus 5 | $0.00083 | $0.00998 |
| Sonnet 5 | $0.00033 | $0.00399 |
| Haiku 4.5 | $0.00017 | $0.00200 |
Grade A, and why
hunting-connection-string-and-jdbc-url-injection scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting connection-string and JDBC-URL injection: when the connection target is attacker-set
Connection strings and driver URLs look like inert configuration, but they are richly featured: they carry the host to connect to and a set of driver properties, and many drivers expose properties that read local files, load classes, run initialization commands, or disable transport security. When an application builds one of these from untrusted input, a tenant identifier, a hostname, a region, or an options blob, the attacker can redirect the connection to a server they control, or append a property that flips a dangerous driver feature on. The result ranges from credential capture at a rogue server to local file reads and code execution through the driver. You find it by locating every place a connection string or URL is built from input and asking which host or property the attacker can set.
When to use
- An application builds a database or service connection string or driver URL from user or tenant input.
- A hostname, port, tenant, region, or driver option in a connection comes from a request or stored value.
- A multi-tenant or dynamic-datasource design selects the connection target at runtime from input.
Scope check
Test connection-string handling only against applications and infrastructure you own or are authorized to assess, on non-production systems. A confirming payload can cause the application to connect to a server you control or trigger a driver feature, so stay inside the authorized boundary and use only endpoints you own as the redirect target. If you can't name the authorization, stop.
The loop
- Establish where connection strings and URLs are built. Inventory every place a connection string, JDBC or driver URL, or datasource is constructed at runtime rather than read whole from fixed configuration. This is the false-positive killer: a connection built entirely from static configuration with no input-derived host or property is not injectable. Name the runtime-built connections first.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 137 lines · 166 tokens per session scan A 3f67b78a9b0c
hunting-connection-string-and-jdbc-url-injection is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 166 tokens to every session and 1,996 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations and post-launch readiness. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line citations…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
linear-claude-skill
Manage Linear issues, projects, and teams.
panguard
AI agent security platform — audit skills, scan for threats, and run 24/7 protection with 9,700+ detection rules.
security-guide
A security deployment guide for OpenClaw, with instructions in English and Chinese. It covers network exposure, container isolation, credentials, permissions, and audit logging.