zkbugs: Skill for Claude Code

.claude/skills/process-audit-report/SKILL.md

process-audit-report is a skill for Claude Code from zksecurity/zkbugs. It costs 38 tokens per session (256 once invoked), scanned A, original, MIT.

A workflow for reading a zero-knowledge circuit security audit report in PDF form and adding its reported vulnerabilities to the zkbugs dataset.

In plain words
What is it for?
Use it with an audit report path to extract circuit bugs, find similar existing entries, create the needed dataset structure and configuration, and verify the results.
Why use it?
It turns findings from an audit into consistently structured dataset entries and includes steps for checking Circom bugs through compilation, setup, tests, and cleanup.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is zksecurity/zkbugs's own configuration. It tells Claude Code how to work on zkbugs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything zkbugs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zksecurity/zkbugs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zksecurity/zkbugs/main/.claude/skills/process-audit-report/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zksecurity/zkbugs

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.

agentmods badge for process-audit-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/zksecurity/zkbugs/process-audit-report.svg)](https://agentmods.dev/skills/zksecurity/zkbugs/process-audit-report)
Your own site
<a href="https://agentmods.dev/skills/zksecurity/zkbugs/process-audit-report"><img src="https://agentmods.dev/badge/skills/zksecurity/zkbugs/process-audit-report.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 256 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00256
Opus 5 $0.00019 $0.00128
Sonnet 5 $0.00008 $0.00051
Haiku 4.5 $0.00004 $0.00026

Measured 6d ago against content hash 17f0a1899d94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

process-audit-report 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 6d 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.

.claude/skills/process-audit-report/SKILL.md · 23 lines

What it actually says

Process Audit Report

Process the audit report at $ARGUMENTS and extract all ZK circuit vulnerabilities into the zkbugs dataset.

Follow prompts/process_audit_report.md for Phase 1 (report parsing) and the summary (Phase 3.3-3.4); it forwards to prompts/_bug_processing.md for Phase 2 and the rest of Phase 3.

For Circom bugs, run the full verification pipeline in section 2.5 of _bug_processing.md (compile + setup + positive test + clean). The "finish the job" guidance, zkbugs_vars.sh handling, and TODO discipline all live in the shared prompt — do not leave TODOs unless you hit a genuine blocker.

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.

  1. 6d ago First seen · 23 lines · 38 tokens per session scan A 17f0a1899d94

Subscribe to this mod's changes

process-audit-report is a skill published in the GitHub repository zksecurity/zkbugs (345 stars, last pushed 17d ago), licensed MIT. It adds 38 tokens to every session and 256 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.