Recon Skills is a pack of security-testing skills covering reconnaissance, web applications, APIs, authentication, vulnerability validation, cloud infrastructure, and reporting. Security professionals use it for authorized assessments of systems they own or have written permission to test. The catalogue entries are individual skills from the pack.
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 uphiago/recon-skills --skill hunt-websocketgit clone --depth 1 https://github.com/uphiago/recon-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/uphiago/recon-skills/hunt-websocket)<a href="https://agentmods.dev/skills/uphiago/recon-skills/hunt-websocket"><img src="https://agentmods.dev/badge/skills/uphiago/recon-skills/hunt-websocket/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/uphiago/recon-skills/hunt-websocket"><img src="https://agentmods.dev/badge/skills/uphiago/recon-skills/hunt-websocket.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high YARA Match · line 66 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 94 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 318 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 | $0.00095 | $0.05149 |
| Opus 5 | $0.00048 | $0.02575 |
| Sonnet 5 | $0.00019 | $0.01030 |
| Haiku 4.5 | $0.00010 | $0.00515 |
Grade A, and why
hunt-websocket scanned grade A 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl --max-time 30 --connect-timeout 10 -sI -o /dev/null -w "%{http_code}\n" \ How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HUNT-WEBSOCKET — WebSocket Security
Crown Jewel Targets
CSWSH (Cross-Site WebSocket Hijacking) with a cookie-authenticated handshake and no CSRF/per-connection token = High–Critical (real-time exfil of any logged-in victim's data).
Highest-value chains:
- CSWSH → data exfil / ATO — handshake authenticates via ambient cookie, no CSRF token, Origin not enforced → attacker page opens WS as the victim and streams their messages/PII/tokens. If the stream carries a session/refresh/CSRF token, this escalates to ATO.
- No per-message auth — HTTP/handshake auth present but individual WS frames are not re-authorized → privileged messages accepted (
deleteUser,getSecretConfig). - Message tampering — modify in-flight frames (price, qty, userId, amount) in trading/game/checkout apps → financial fraud.
- socket.io namespace / room authz bypass — connect to a privileged namespace or join another user's room without a permission check → cross-tenant real-time exfil.
- Handshake-layer Upgrade smuggling — a malformed
Upgrade/Connection/Sec-WebSocket-*handshake makes the front proxy and origin disagree on whether an upgrade occurred → request-smuggling tunnel.
Grounding — Reference Cases (read before hunting)
These are public, verifiable references. Use them to calibrate what a real WS finding looks like and how it was proven. Do not invent additional report IDs or payouts.
| # | Source / ID | Class | Lesson |
|---|---|---|---|
| 1 | PortSwigger Web Security Academy — "Cross-site WebSocket hijacking" (research + labs) | CSWSH | Canonical CSWSH model: cookie-auth handshake + no CSRF token + missing Origin check → attacker reads/sends as victim. The authoritative methodology. |
| 2 | Christian Schneider — "Cross-Site WebSocket Hijacking (CSWSH)" (original disclosure/write-up, 2013) | CSWSH | First public CSWSH technique: cookie-auth handshake + no Origin enforcement; PoC must prove victim-data receipt in the attacker browser, not just a 101. |
| 3 | Coda CSWSH (referenced in this repo's hunt-csrf set) | CSWSH | Real-time collab apps commonly authenticate the socket purely via cookie; Origin allow-listing was the missing control. |
| 4 | CVE-2020-7662 — websocket-extensions (Node) ReDoS |
DoS | A crafted Sec-WebSocket-Extensions header triggers catastrophic backtracking — handshake header is an attack surface, not just frames. |
| 5 | CVE-2024-37890 — ws (Node) DoS |
DoS | Many handshake request headers exhaust the server; confirms the handshake itself is parser-attackable pre-frames. |
| 6 | Outdated socket.io / Engine.IO stacks |
socket.io | Motivates the version-fingerprint step in Phase 7 — fingerprint the version, then check that release's known advisories. |
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.
- 6d ago First seen · 325 lines · 95 tokens per session scan A db980d05ba31
hunt-websocket is a skill published in the GitHub repository uphiago/recon-skills (1,251 stars, last pushed 8d ago), licensed MIT. It adds 95 tokens to every session and 5,149 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
securing-api-gateway-with-aws-waf
Securing API Gateway endpoints with AWS WAF by configuring managed rule groups for OWASP Top 10 protection, creating custom rate limiting rules, implementing bot control, setting up IP reputation filtering, and monitoring WAF metrics for security effectiveness.
graphql-audit
GraphQL security hunting — introspection abuse, field suggestion enumeration (clairvoyance), batching DoS, IDOR via aliasing, auth bypass, injection via arguments, subscription abuse, depth/complexity bombs, and WAF bypass. Covers graphw00f fingerprinting, gqlmap, graphql-cop, and inql. Use when a target exposes a…
detecting-broken-object-property-level-authorization
Detect and test for OWASP API3:2023 Broken Object Property Level Authorization vulnerabilities including excessive data exposure and mass assignment attacks.
exploiting-broken-function-level-authorization
Tests APIs for Broken Function Level Authorization (BFLA) vulnerabilities where regular users can invoke administrative functions or access privileged API endpoints by directly calling them. The tester identifies admin and privileged endpoints, then attempts to access them with regular user credentials by manipulating…
exploiting-excessive-data-exposure-in-api
Tests APIs for excessive data exposure where endpoints return more data than the client application needs, relying on the frontend to filter sensitive fields. The tester intercepts API responses and analyzes them for leaked PII, internal identifiers, debug information, or sensitive business data that the UI does not…
performing-api-inventory-and-discovery
Performs API inventory and discovery to identify all API endpoints in an organization's environment including documented, undocumented, shadow, zombie, and deprecated APIs. The tester uses passive traffic analysis, active scanning, DNS enumeration, JavaScript analysis, and cloud resource inventory to build a…