What is hunt-injection?

A security-testing guide for GraphQL, XXE, and SSTI vulnerabilities. GraphQL is an API query system; XXE can make XML processors read files or access other systems; SSTI happens when user input is treated as a template and may lead to code execution.

Use it to test GraphQL schemas, XML uploads such as SVG, DOCX, and SAML, server-side templates, and related file-reading, request-forgery, or code-execution paths.

It helps identify these injection problems and distinguish genuine access or code-execution issues from harmless errors or blocked payloads.

hunt-injection — Skill for Claude Code by Encod3d-Sec

Install

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.

Any agent

npx skills add Encod3d-Sec/TORCH --skill hunt-injection

Clone the repo

git clone --depth 1 https://github.com/Encod3d-Sec/TORCH

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/encod3d-sec/torch/hunt-injection.svg)](https://agentmods.dev/skills/encod3d-sec/torch/hunt-injection)

Your own site

<a href="https://agentmods.dev/skills/encod3d-sec/torch/hunt-injection"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/hunt-injection.svg" alt="Measured on agentmods" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,166 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 5 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 Privilege Escalation · line 63
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
high Privilege Escalation · line 79
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
high Privilege Escalation · line 145
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
high Server-Side Request Forgery · line 134
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 33
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.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00051	$0.02166
Opus 5	$0.00026	$0.01083
Sonnet 5	$0.00010	$0.00433
Haiku 4.5	$0.00005	$0.00217

Measured 8d ago against content hash a742cfc53de6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

hunt-injection scanned grade B with 2 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 8d 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.

Cloud metadata endpointmediumServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

<!ENTITY xxe SYSTEM "http://169.254.169.254/latest/meta-data/iam/security-credentials/">

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 \

skills/hunt/hunt-injection/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hunt: GraphQL / XXE / SSTI

Assumes hunt-core for the scope gate, two-account rule, confirmation gate, enumeration limits, stop conditions, wiki protocol, FIND output, and Deadends. Do not re-derive any of that here.

Wiki

qmd_query "SSTI XXE GraphQL injection template injection XML external entity" via wiki-search MCP

Hub: [[web-moc]] (live web index). Primary page: [[ssti]]. Payload arsenals: wiki/payloads/{ssti,xxe,graphql,xslt}.md. Anchors: [[xxe]], [[graphql-attacks]], [[xslt-injection]] (server-side XSLT injection, payloads [[xslt]]).

GRAPHQL

Signals

/graphql  /api/graphql  /v1/graphql  /query  /gql
POST requests with {"query": "..."} body in Burp history
"apollo", "ApolloClient", "gql`" in JS bundles

Methodology

Test introspection:

curl -s -X POST https://target.com/graphql \
  -H "Content-Type: application/json" \
  -d '{"query":"{ __schema { queryType { fields { name } } } }"}'

If blocked, try: {"query":"{ __typename }"}

Use InQL (Burp extension) or graphql-voyager to map schema. Push load-bearing queries/mutations to Burp Repeater (Skill(hunt-burp) / the Burp MCP) so the operator can replay them.
Find REST/GraphQL overlap - resources modifiable via BOTH APIs
Test IDOR: replay queries/mutations with another user's object IDs
Test authorization: lower-privilege user calling admin mutations
Test for persistent privilege after REST revokes access - GraphQL re-grants?

Evasion

Introspection disabled -> {"query":"{ __typename }"} confirms GraphQL is live; then field-suggestion mining (typo a field, the error often names valid ones), alias-based enumeration for parallel object access, and query batching (array body) to bypass per-request rate limits and some auth checks.

XXE

Attack Surface (ranked)

/upload  /import  /parse  /convert  /saml/acs  /soap/*
Content-Type: application/xml or text/xml
SVG, DOCX, XLSX, PPTX file upload features

Rank: SAML ACS and document/office upload converters first (parsers there routinely resolve external entities), then any endpoint you can flip to Content-Type: application/xml.

Read the full file on GitHub · 173 lines

Changes

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.

8d ago First seen · 173 lines · 51 tokens per session scan B a742cfc53de6

Subscribe to this mod's changes

hunt-injection is a skill published in the GitHub repository Encod3d-Sec/TORCH (314 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 2,166 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (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.

Security Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

hunt-injection