Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
citation-audit
citation-audit is an open-source security skill for Claude Code and compatible agents, published by wanshuiyin. Its author describes it as: “Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated ven…”. The project has 15k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/citation-audit`.
What citation-audit does
> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It is > verdict-bearing — it judges bibliographic correctness. Re-running that verdict > on a timer adds no new signal (it changes only when the *bibliography* > changes). Schedule the *external wait that precedes it* — bibliography > finalized → then audit **once**. See > `shared-references/external-cadence.md`.
Installation
Add citation-audit to your agent with:
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/citation-auditAlways review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.
What's inside
The SKILL.md for citation-audit is organised into these sections:
- When to Use This Skill
- What This Skill Catches
- Constants
- Workflow
- Step 1: Discover bib file and section files
- Step 2: Extract all (cite-key, context) pairs
- Step 3: Send each entry to fresh cross-model reviewer
- Step 4: Aggregate verdicts
- Step 5: Generate human-readable report
- Step 6: Apply fixes (interactive)
- Step 7: Recompile and verify
- Uncited Entry Detection (opt-in)
When to use it
Reach for citation-audit when you want security help from your agent without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.
Strengths
- Clear MIT license — safe to read and adapt
- Ships in wanshuiyin/Auto-claude-code-research-in-sleep, an established project with 14,858 GitHub stars
- Actively maintained (recent commits)
Topics
Frequently asked questions
- What does citation-audit do?
- Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.
- How do I install citation-audit?
- Run git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/citation-audit in your agent, then reload your skills. Review the source at https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep before installing.
- Is citation-audit free to use?
- Yes. citation-audit is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Where does citation-audit come from?
- citation-audit ships inside wanshuiyin/Auto-claude-code-research-in-sleep, a repository that contains 41 catalogued skills in total. The repository's 14,858 GitHub stars apply to that whole collection, not to this skill on its own.
Related skills
More Security →
Master smart contract security best practices to prevent common vulnerabilities and implement secure Solidity patterns. Use when writing smart contracts, auditing existing contracts, or implementing security measures for blockchain applications.
Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more
State-of-the-Art (2026) AI/LLM engineering skills/agents for building and auditing software — 40+ domain & language skills, BUILD/AUDIT modes, audit checklists.
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches. AI agents running in CI/CD pipelines.