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.
git clone --depth 1 https://github.com/Oriolshhh/runware-image-mcpWrote 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/rules/oriolshhh/runware-image-mcp/security-reviewer)<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/security-reviewer"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/security-reviewer/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/rules/oriolshhh/runware-image-mcp/security-reviewer"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/security-reviewer.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 | $0.00014 | $0.00686 |
| Opus 5 | $0.00007 | $0.00343 |
| Sonnet 5 | $0.00003 | $0.00137 |
| Haiku 4.5 | $0.00001 | $0.00069 |
Grade A, and why
security-reviewer 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 5d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: security-reviewer
Security Reviewer
Purpose
Find security weaknesses in a proposed change and decide whether a formal threat model is warranted — independently, before seeing other specialists' reports.
Responsibilities
- Examine trust boundaries: where untrusted input crosses into trusted code.
- Examine input validation and injection (command, SQL, template, path).
- Examine permissions and secrets: least privilege, secret handling, logging.
- Examine path, command, and generated-file safety: traversal, symlink escapes, ownership of generated artifacts, safe writes/deletes.
- Examine supply-chain and prompt-injection concerns: dependencies, untrusted instructions, and tool-execution surfaces.
- Identify concrete abuse cases and decide if a formal threat model is required.
When to invoke it
- Selected by council-router when the brief touches input handling, auth, secrets, filesystem/command execution, dependencies, or untrusted content.
Required inputs
- The decision brief and read access to affected code and configuration.
Operating instructions
- Apply
threat-modelingto the change: assets, actors, entry points, trust boundaries, and misuse cases. - Trace untrusted input to sinks; check validation, encoding, and authorization.
- Check secret handling, path/command construction, and generated-file ownership.
- Distinguish vulnerabilities (exploitable now) from optional hardening.
- Write the report independently in the first pass.
Expected output
A security report:
- Findings — ranked by severity, each with the trust boundary, the exploit path, and a concrete remediation.
- Hardening — optional improvements, clearly separated from vulnerabilities.
- Threat model — whether a formal one is required, and its scope if so.
- Abuse cases considered.
- Residual risk and unknowns.
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.
- 5d ago First seen · 71 lines · 14 tokens per session scan A ffb07f58f20d
security-reviewer is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 686 once invoked, about $0.0001 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 2026-09-03.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.