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 gmh5225/awesome-llvm-security --skill static-analysisgit clone --depth 1 https://github.com/gmh5225/awesome-llvm-securityWrote 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/gmh5225/awesome-llvm-security/static-analysis)<a href="https://agentmods.dev/skills/gmh5225/awesome-llvm-security/static-analysis"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-llvm-security/static-analysis.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.01730 |
| Opus 5 | $0.00024 | $0.00865 |
| Sonnet 5 | $0.00010 | $0.00346 |
| Haiku 4.5 | $0.00005 | $0.00173 |
Grade A, and why
static-analysis 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Static Analysis Skill
This skill covers static program analysis techniques using LLVM infrastructure for security research, vulnerability detection, and code quality assessment.
Analysis Categories
Dataflow Analysis
- Forward Analysis: Track values from definitions to uses
- Backward Analysis: Track from uses back to definitions
- May/Must Analysis: Conservative vs precise approximations
Control Flow Analysis
- Dominator Trees: Identify code dominance relationships
- Post-Dominator Trees: Control dependence analysis
- Loop Analysis: Detect and characterize loops
Pointer Analysis
- Flow-Insensitive: Andersen's, Steensgaard's algorithms
- Flow-Sensitive: Track pointer values at each program point
- Context-Sensitive: Distinguish calling contexts
LLVM Analysis Infrastructure
Using Built-in Analyses
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/DominatorTree.h"
void analyze(llvm::Function& F, llvm::FunctionAnalysisManager& FAM) {
// Get dominator tree
auto& DT = FAM.getResult<llvm::DominatorTreeAnalysis>(F);
// Get loop info
auto& LI = FAM.getResult<llvm::LoopAnalysis>(F);
// Get alias analysis
auto& AA = FAM.getResult<llvm::AAManager>(F);
// Check if two pointers may alias
llvm::AliasResult AR = AA.alias(Ptr1, Ptr2);
}
Implementing Custom Analysis
class TaintAnalysis {
std::set<llvm::Value*> taintedValues;
public:
void markTainted(llvm::Value* V) {
taintedValues.insert(V);
}
bool isTainted(llvm::Value* V) {
return taintedValues.count(V) > 0;
}
void propagate(llvm::Instruction* I) {
// Propagate taint through operations
for (auto& Op : I->operands()) {
if (isTainted(Op)) {
markTainted(I);
break;
}
}
}
};
Taint Analysis
Source-Sink Model
// Define taint sources (user input, network, files)
bool isTaintSource(llvm::CallInst* CI) {
llvm::Function* F = CI->getCalledFunction();
if (!F) return false;
static const std::set<std::string> sources = {
"read", "recv", "fread", "getenv", "gets", "scanf"
};
return sources.count(F->getName().str()) > 0;
}
// Define sensitive sinks (SQL queries, system calls, format strings)
bool isSensitiveSink(llvm::CallInst* CI) {
llvm::Function* F = CI->getCalledFunction();
if (!F) return false;
static const std::set<std::string> sinks = {
"system", "exec", "printf", "strcpy", "memcpy", "sql_query"
};
return sinks.count(F->getName().str()) > 0;
}
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.
- 7d ago First seen · 249 lines · 48 tokens per session scan A 1e71572a108d
static-analysis is a skill published in the GitHub repository gmh5225/awesome-llvm-security (879 stars, last pushed 23d ago), licensed MIT. It adds 48 tokens to every session and 1,730 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Deobfuscation
Systematic binary deobfuscation — string decryption, control flow flattening (CFF) removal, opaque predicate elimination, mixed boolean-arithmetic (MBA) simplification, bogus control flow, instruction substitution reversal, dead code removal, and anti-disassembly fixes. Trigger: deobfuscate, unobfuscate…
defeating-control-flow-flattening
Defeats control-flow-flattening obfuscation by identifying the dispatcher/state- variable structure and reconstructing the original control flow so the logic becomes readable. Activates for requests to defeat control-flow flattening, deobfuscate an OLLVM-flattened function, or recover original control flow from a…
stop-chasing-the-optimizer-reduce-instead
After two failed anti-optimization patches, stop and reduce; don't keep bolting on volatile / noinline.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.