Borrowing it
Nothing to install: this file belongs to Smart-AI-Memory/attune-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/attune-ai/main/.agents/skills/security-audit/SKILL.mdgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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/smart-ai-memory/attune-ai/security-audit)<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/security-audit"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/security-audit/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/smart-ai-memory/attune-ai/security-audit"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 34 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00054 | $0.00884 |
| Opus 5.5 | $0.00022 | $0.00354 |
| Sonnet 5.5 | $0.00011 | $0.00177 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
security-audit 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 1mo 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit
IMPORTANT: Start your response with a context preamble.
Call help_lookup(topic="security-audit", mode="preamble") and
display the returned preamble text as a blockquote. Then
tell the user they can say "tell me more" for a step-by-step
guide, or answer the scoping questions below to proceed.
If the MCP call fails, fall back to:
Security Audit — Scans your code for security vulnerabilities — eval/exec, path traversal, hardcoded secrets, injection risks.
Scoping
Before running, ask:
- Scope: "Which path should I scan?" Default to the project root if the user says "everything."
- Focus: "Any specific concern — secrets, injection, dependencies, or a full sweep?"
Execution
Shared command workspace (preferred)
Open adapter security-audit with the validated path and focus. The invocation
authorizes this read-only scan, so the running workspace has no confirmation
action. Call security_audit and publish its exact outcome as scan_result,
including health score, files scanned, and categorized path/line/severity/CWE
findings. An incomplete scan must say “did not complete,” never “clean.”
Critical/high findings render one per page with bound Previous/Next actions,
avoiding a tall unscrollable form. finish_security_audit records the report;
handoff_to_fix prepares an explicit Fix input containing all critical/high
receipts but performs no mutation. Fix retains its own exact-command approval.
Present the terminal widget or Markdown and preserve the same pagination,
failure, and handoff semantics in text fallback.
Call the security_audit MCP tool with the scoped path:
security_audit(path="<user-specified path>")
Output Format
The security_audit tool returns a health_score, the summary_markdown,
and a pre-rendered panel_html (present on the report path).
Prefer the rich panel. Pass the response's panel_html straight to
mcp__visualize__show_widget — it renders the report's sections
(findings cards and/or category bullet lists — security / quality /
performance / architecture) under the title + score. Display-only and
injection-safe (generated by attune.workflows.report_panel, the
universal renderer shared by every analysis workflow). A failed run shows
an explicit "did not complete" state, never a false "clean".
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.
- 1mo ago Changed · +15 lines 2e6a7b53a474
- 1mo ago First seen · 101 lines · 54 tokens per session scan A 1b1931030d0b
security-audit is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 884 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
pod-chat-tone
In-product voice rewrite for agents posting to Commonly pods — kills the report-in-a-chatbox shape (bold-lead sentences, ✅/❌ ladders, em-dash density, mirror clauses, self-narration of one's own reasoning) that makes agent rooms unreadable to the humans they are for. Mandatory pre-post pass on every pod message.…
pandic-office
Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
lynkr
Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.
commonly-design
Use this skill for ANY visual / UI / design work on Commonly — picking colors, choosing fonts, styling new v2 components, building HTML mocks, designing marketing pages, or auditing whether a change matches the brand. Triggers on tasks involving v2.css tokens, accent / blue / focus ring / SF font, brand mark / logo…
web-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.