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 agentmods add skills/zfinix/aster/security-reviewnpx skills add Zfinix/aster --skill security-reviewgit clone --depth 1 https://github.com/Zfinix/asterWrote 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/zfinix/aster/security-review)<a href="https://agentmods.dev/skills/zfinix/aster/security-review"><img src="https://agentmods.dev/badge/skills/zfinix/aster/security-review.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.01131 |
| Opus 5 | $0.00028 | $0.00566 |
| Sonnet 5 | $0.00011 | $0.00226 |
| Haiku 4.5 | $0.00006 | $0.00113 |
Grade A, and why
security-review 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 4d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security review
Review the diff as an attacker would. Only report issues introduced or exposed by the changed lines; pre-existing problems get one summary line at most, not findings.
What to hunt, in order of impact
- Injection. String-built SQL, shell commands with interpolated input, LDAP/ORM raw fragments, template injection. Parameterize or escape; name the exact concatenation site.
- Broken authorization. Endpoints and handlers that authenticate but never
check ownership or role (
user_idfrom the request instead of the session). IDOR: any resource fetched by an ID the client controls without an ownership check. - Unvalidated input reaching dangerous sinks. Path traversal
(
PathBuf::join/path.joinwith user segments), open redirects, SSRF (user-supplied URLs fetched server-side), unsafe deserialization of untrusted bytes. - Output escaping. User data rendered into HTML, markdown, shell output,
logs, or SQL identifiers without escaping;
innerHTML,dangerouslySetInnerHTML, unescaped template variables. - Secrets and credentials. Hardcoded keys, tokens in URLs, secrets logged, credentials in error messages returned to clients.
- Crypto and session. Weak hashes for passwords (anything unsalted or
non-argon2/bcrypt/scrypt),
Math.random/naive RNG for tokens, missing expiry or signature checks, comparisons of secrets with==instead of constant-time. - Web plumbing. Missing CSRF protection on state-changing routes, CORS
widened to
*with credentials, cookies withoutHttpOnly/Secure/SameSite, permissive file-upload type checks. - AI/LLM integration. Provider API keys shipped to the client bundle, no spend cap on model calls, untrusted content concatenated into prompts (prompt injection), model output rendered as HTML/markdown or passed to a tool without validation.
Detection commands
Run these over the changed files first; each hit is a candidate to trace by hand, not a finding on its own:
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.
- 4d ago First seen · 94 lines · 55 tokens per session scan A 17e9bbe140a5
security-review is a skill published in the GitHub repository Zfinix/aster (43 stars, last pushed 2d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,131 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
om-integration-builder
Build integration provider packages for the Open Mercato Integration Marketplace (payment, shipping, data-sync, webhook). Scaffolds the npm package, adapter, credentials, widget injection, webhook processing, health checks, i18n, tests. Triggers on "build integration", "add provider", "integrate with…
moai-foundation-core
Provides MoAI-ADK foundational principles including TRUST 5 quality framework, SPEC-First DDD methodology, delegation patterns, progressive disclosure, agent catalog reference, and token budget management (absorbed from moai-foundation-context). Use when referencing TRUST 5 gates, SPEC workflow, or context window…
portfolio
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…
bitfun-canvas
A BitFun Canvas is a live React app that the user can open beside the chat. You MUST use a canvas when the agent produces a standalone analytical artifact — quantitative analyses, billing investigations, security audits, architecture reviews, data-heavy content, timelines, charts, tables, interactive explorations…
om-create-ai-agent
Build, override, or extend a typed Open Mercato AI agent (chat or structured-object) using the unified AI framework — declare ai-agents.ts, register tool packs via defineAiTool, patch existing agents with aiAgentExtensions, configure agentic loop controls (loop.stopWhen / loop.prepareStep / loop.budget /…
memstack-business-scope-of-work
Use this skill when the user says 'scope of work', 'SOW', 'define scope', 'project scope', 'write SOW', 'scope document', or is defining project boundaries, deliverables, and acceptance criteria for a formal engagement. Do NOT use for proposals, contracts, or invoicing.