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 Zhang-Henry/CoEvoSkills --skill evo-suricata-http-exfilgit clone --depth 1 https://github.com/Zhang-Henry/CoEvoSkillsWrote 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/zhang-henry/coevoskills/evo-suricata-http-exfil)<a href="https://agentmods.dev/skills/zhang-henry/coevoskills/evo-suricata-http-exfil"><img src="https://agentmods.dev/badge/skills/zhang-henry/coevoskills/evo-suricata-http-exfil/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/zhang-henry/coevoskills/evo-suricata-http-exfil"><img src="https://agentmods.dev/badge/skills/zhang-henry/coevoskills/evo-suricata-http-exfil.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 | $0.00064 | $0.01124 |
| Opus 5 | $0.00032 | $0.00562 |
| Sonnet 5 | $0.00013 | $0.00225 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade C, and why
evo-suricata-http-exfil scanned grade C with 1 finding 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 9d 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.
Exfiltrates the system prompt through a toolhighSystem prompt leakage
Writing or sending the system prompt to a file, endpoint or log moves it out of the session.
- `write_rules_file(rules_path, rules)` - Write rules to a file How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suricata HTTP Exfiltration Detection Rule Skill
This skill provides reusable functions for generating Suricata rules that detect HTTP-based data exfiltration. It handles:
- Building rules with HTTP sticky buffers (http.method, http.uri, http.header, http.request_body)
- Exact URI matching with bsize
- Header name:value matching with CRLF boundary and optional case-insensitivity
- Body field matching with URL-encoded field boundary checks to prevent substring false positives
- Syntax validation via
suricata -T - Functional validation against positive/negative pcap files
Key Technical Details
HTTP Sticky Buffers
http.method- matches the HTTP method (GET, POST, etc.)http.uri- matches the normalized URI path; usebsize:Nfor exact lengthhttp.header- matches raw request headershttp.request_body- matches the HTTP request body
Header Matching Best Practices
- HTTP header names are case-insensitive per RFC 7230; use
nocaseto handle variations - Append
|0d 0a|(CRLF) after the header value to prevent substring false positives (e.g., header value "exfil" should not match "exfiltrate") - The
http.headerbuffer contains raw headers as sent by the client
Body Field Boundary Matching
In URL-encoded bodies (application/x-www-form-urlencoded), fields are separated
by & and the first field starts at the beginning of the body. A naive
content:"blob=" would match xblob= as a substring.
The correct approach uses PCRE with field boundary checks:
pcre:"/(?:^|&)fieldname=VALUE_PATTERN/"
This ensures fieldname is either at the start of the body or preceded by &.
PCRE with /R Flag
/Rmeans "relative to last content match"- When not using a preceding content anchor, omit
/Rto search the entire buffer - Use
(?:^|&)for URL-encoded field boundary matching
Common Pitfalls
bsizemust exactly equal the URI string length (count carefully)- Content matches are substring matches; use field boundaries to prevent false positives
- Header names in
http.headerbuffer are raw (not normalized for case) flow:to_server,establishedensures we match client requests in established TCP sessions- All conditions within a single rule are conjunctive (AND)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 105 lines · 64 tokens per session scan C fd587f3607be
evo-suricata-http-exfil is a skill published in the GitHub repository Zhang-Henry/CoEvoSkills (66 stars, last pushed 23d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,124 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (exfiltrates the system prompt through a tool). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…