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 agentmods add skills/shulkwisec/bb-huge/expression-language-injectionnpx skills add ShulkwiSEC/bb-huge --skill expression-language-injectiongit clone --depth 1 https://github.com/ShulkwiSEC/bb-hugeWrote 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/shulkwisec/bb-huge/expression-language-injection)<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/expression-language-injection"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/expression-language-injection.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.02327 |
| Opus 5 | $0.00023 | $0.01163 |
| Sonnet 5 | $0.00009 | $0.00465 |
| Haiku 4.5 | $0.00005 | $0.00233 |
Grade A, and why
expression-language-injection scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to expression-language-injection — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Expression Language Injection — Expert Attack Playbook
AI LOAD INSTRUCTION: Expert EL injection techniques covering SpEL (Spring), OGNL (Struts2), and Java EL (JSP/JSF). Distinct from SSTI — EL injection targets expression evaluators in Java frameworks, not template engines. Covers sandbox bypass,
_memberAccessmanipulation, actuator abuse, and real-world CVE chains.
0. RELATED ROUTING
- ssti-server-side-template-injection for template engines (Jinja2, FreeMarker, Twig) — different attack surface
- jndi-injection when EL evaluation leads to JNDI lookup
Key distinction: SSTI targets template rendering engines; EL injection targets expression evaluators embedded in Java frameworks. They share detection probes (${7*7}) but diverge in exploitation.
1. DETECTION — POLYGLOT PROBES
${7*7} → 49 = SpEL, OGNL, or Java EL
#{7*7} → 49 = SpEL (alternative syntax) or JSF EL
%{7*7} → 49 = OGNL (Struts2)
${T(java.lang.Math).random()} → random float = SpEL confirmed
%{#context} → object dump = OGNL confirmed
Disambiguation
Response to ${7*7} |
Response to %{7*7} |
Engine |
|---|---|---|
| 49 | literal %{7*7} |
SpEL or Java EL |
literal ${7*7} |
49 | OGNL (Struts2) |
| 49 | 49 | Both may be active |
2. SpEL (SPRING EXPRESSION LANGUAGE)
Where SpEL Appears
@Value("${...}")annotations- Spring Security expressions (
@PreAuthorize) - Spring Cloud Gateway route predicates and filters
- Thymeleaf
th:text="${...}"(when combined with__${...}__preprocessing) - Spring Data
@Querywith SpEL
RCE via Runtime.exec
${T(java.lang.Runtime).getRuntime().exec("id")}
RCE with Output Capture (Commons IO)
${T(org.apache.commons.io.IOUtils).toString(T(java.lang.Runtime).getRuntime().exec("id").getInputStream())}
RCE with Output Capture (Spring StreamUtils)
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.
- 2d ago First seen · 244 lines · 45 tokens per session scan A dd96ba349b08
expression-language-injection is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 2,327 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to expression-language-injection, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
skill-context-detection
Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type.
skill-copilot-provider
GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode.
bugcrowd-reporting
Bugcrowd-specific reporting tactics complementing report-writing: VRT category search-and-fallback strategy when no exact match exists, manual severity override when VRT defaults underrate impact, severity-request paragraph as first body section, OOS-clause rebuttal templates (rate limiting on auth-flow endpoints…
race
Race condition / TOCTOU playbook — limit overrun (one-time codes used twice, gift cards spent twice), single-packet attack (last-byte sync) to force parallel processing, and state-confusion races (file upload + read, order before payment). Use when timing-sensitive logic could be abused — one-time codes, coupons/gift…
skill-security-framing
URL validation and content sanitization for untrusted sources — use when handling external input safely.
my-skill
One line on what this playbook does, then a "Use when ..." clause so the agent knows when to load it (e.g. "Use when the target exposes X / you see Y in requests"). Max 1024 chars. This description is the ONLY thing the model sees until it loads the skill — make the trigger conditions explicit, since there is no…