claude-red is a library of structured skills that give Claude specialized offensive-security methods for areas such as web vulnerabilities, shellcode, exploit development, and identity systems. It is intended for authorized red-team work, bug-bounty triage, security research, CTF preparation, and operator training. Its catalogue contains the project's skills for loading these security specializations into Claude.
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 SnailSploit/Claude-Red --skill offensive-graphqlgit clone --depth 1 https://github.com/SnailSploit/Claude-RedWrote 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/snailsploit/claude-red/offensive-graphql)<a href="https://agentmods.dev/skills/snailsploit/claude-red/offensive-graphql"><img src="https://agentmods.dev/badge/skills/snailsploit/claude-red/offensive-graphql/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/snailsploit/claude-red/offensive-graphql"><img src="https://agentmods.dev/badge/skills/snailsploit/claude-red/offensive-graphql.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 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 Server-Side Request Forgery · line 250 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- high Server-Side Request Forgery · line 519 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- medium Data Exfiltration · line 32 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 156 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 281 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 281 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00219 | $0.05189 |
| Opus 5.5 | $0.00088 | $0.02076 |
| Sonnet 5.5 | $0.00044 | $0.01038 |
| Haiku 4.5 | $0.00022 | $0.00519 |
Grade B, and why
offensive-graphql scanned grade B with 3 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.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
r = requests.post("https://target.com/graphql", json=ops[i:i+500], Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
mutation { setAvatar(url: "http://169.254.169.254/latest/meta-data/iam/security-credentials/") { success } } Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST https://target.com/graphql \ Copies of this mod
1 near-identical copy found in the catalogue:
- offensive-graphql — 88% identical, 42 lines differ
How it starts
The opening of the file, as written. The whole thing — 568 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Offensive GraphQL
GraphQL consolidates an entire API surface behind a single endpoint, making it a high-value target during web application assessments. Unlike REST, where each route maps to a discrete resource, a GraphQL schema exposes every type, field, mutation, and subscription in one queryable structure. Attackers who obtain or reconstruct that schema gain a complete map of the application's data model before writing a single exploit. This skill walks you through each phase of a GraphQL engagement with concrete queries, tool invocations, and chaining patterns.
Quick Workflow
- Discover the endpoint -- probe common paths, inspect client-side JS bundles, check WebSocket upgrade headers.
- Fingerprint the implementation -- use graphw00f to identify the engine and tailor payloads.
- Dump or reconstruct the schema -- full introspection query; if blocked, field suggestion probing or clairvoyance.
- Map the attack surface -- feed the schema into GraphQL Voyager or InQL.
- Test authentication and authorization -- every query and mutation with no token, low-privilege, and cross-user tokens.
- Inject through resolvers -- SQL, NoSQL, and OS command payloads through arguments and variables.
- Abuse batching -- arrayed operations for brute force, OTP bypass, and rate limit evasion.
- Stress depth and complexity -- nested queries, alias fans, and circular fragments.
- Probe subscriptions -- WebSocket with expired or missing tokens, subscribe to sensitive streams.
- Exfiltrate via errors -- verbose stack traces, type mismatches, field suggestions.
- Test file upload -- multipart GraphQL specification for oversized or malicious files.
- Chain and escalate -- combine findings into multi-step attack paths with proof-of-concept queries.
1 -- Endpoint Discovery and Fingerprinting
Probe common paths with a minimal query body. A __typename response confirms a live GraphQL endpoint.
curl -s -X POST https://target.com/graphql \
-H "Content-Type: application/json" \
-d '{"query":"{__typename}"}' | jq .
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 First seen · 568 lines · 219 tokens per session scan B fb88732fb1cc
offensive-graphql is a skill published in the GitHub repository SnailSploit/Claude-Red (7,620 stars, last pushed 8d ago), licensed MIT. It adds 219 tokens to every session and 5,189 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it B with 3 findings (sends data to an external url, cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
api-security-best-practices
Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities.
agent-ready-dns-aid
Sub-skill: Implement DNS-AID records so agents discover endpoints through DNS. Use SVCB/HTTPS records under agents namespace with alpn and connection parameters.
agent-ready-markdown-negotiation
Sub-skill de agent-ready-cloudflare: Implement Markdown Content Negotiation.
agent-ready-api-catalog
Sub-skill de agent-ready-cloudflare: Implement API Catalog.
agent-ready-link-headers
Sub-skill de agent-ready-cloudflare: Implement Link Response Headers.
agent-ready-mcp-server-card
Sub-skill de agent-ready-cloudflare: Implement MCP Server Card.