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 EresusSecurity/appsec-skills --skill eresus-variant-analysisgit clone --depth 1 https://github.com/EresusSecurity/appsec-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/eresussecurity/appsec-skills/eresus-variant-analysis)<a href="https://agentmods.dev/skills/eresussecurity/appsec-skills/eresus-variant-analysis"><img src="https://agentmods.dev/badge/skills/eresussecurity/appsec-skills/eresus-variant-analysis/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/eresussecurity/appsec-skills/eresus-variant-analysis"><img src="https://agentmods.dev/badge/skills/eresussecurity/appsec-skills/eresus-variant-analysis.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00085 | $0.01068 |
| Opus 5 | $0.00043 | $0.00534 |
| Sonnet 5 | $0.00017 | $0.00214 |
| Haiku 4.5 | $0.00009 | $0.00107 |
Grade A, and why
eresus-variant-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 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.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GHSA / CVE Variant Analysis
Purpose
When a known vulnerability (GHSA, CVE, or manually discovered bug) is identified, systematically search the entire codebase for similar patterns. The goal is to find every instance of the same underlying weakness — not just the one that was reported.
This skill operates like a GitHub Security Lab researcher performing variant analysis after a vulnerability disclosure.
Workflow
Phase 1: Decompose the Known Vulnerability
Extract the structural components of the known bug:
- Source — where does attacker-controlled data enter?
- Sink — which dangerous API/function receives the data?
- Missing guard — what validation/sanitization is absent?
- Trust boundary — which trust boundary was violated?
- Language pattern — what does the vulnerable code look like structurally?
Example decomposition:
CVE-2024-XXXX:
Source: HTTP request body → `req.body.username`
Sink: `db.query("SELECT * FROM users WHERE name = '" + username + "'")`
Missing guard: No parameterized query, no input sanitization
Trust boundary: User input → Database query
Pattern: String concatenation in SQL query construction
Phase 2: Generalize the Pattern
Abstract away specific variable names and file paths to create search queries:
- Exact sink search — search for the dangerous function/method name
- Pattern search — search for the structural pattern (e.g., string concatenation + SQL keywords)
- Framework search — search for framework-specific equivalents
Use view_file and grep_search to locate all candidate instances.
Phase 3: Triage Each Match
For every match found, answer these questions:
- Is the source actually attacker-controlled in this context?
- Is the sink reachable from the source in the execution flow?
- Are there mitigations present that neutralize this specific instance?
- Does the framework provide implicit protection here?
Classify each match:
- CONFIRMED — same pattern, exploitable, no mitigation
- LIKELY — same pattern, probably exploitable, needs deeper trace
- MITIGATED — same pattern exists but protection is present
- FALSE POSITIVE — pattern match but not actually exploitable
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 · 138 lines · 85 tokens per session scan A b9af6ba1214e
eresus-variant-analysis is a skill published in the GitHub repository EresusSecurity/appsec-skills (7 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,068 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
ai-skill-auditor
A universal, dependency-free Node.js tool to statically audit AI Skills and local agents for malicious patterns.
smart-contract-audit
Comprehensive smart contract security audit framework with multi-expert analysis. Use for full audits of Ethereum / EVM Solidity and Vyper, Solana / SVM Anchor Rust, TON / FunC / Tact, or Sui / Move projects.
infrastructure-audit
Comprehensive infrastructure security audit framework for IaC, Docker, Kubernetes, and cloud configurations. Use for full infrastructure audits.
broken-access-control
Replay captured requests with swapped identities and bumped object IDs to surface broken access control. Use when testing for IDOR or authz flaws.
jwt-attacks
Forge and re-sign captured JWTs to test signature validation - algorithm confusion (alg:none, RS256 to HS256), key injection, and secret cracking. Use when testing JWT or bearer-token auth.
external-enumeration
Passively map a company's domains, subdomains, DNS ownership, tech stack, and CDNs. Use to recon an external attack surface or enumerate subdomains.