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 buzzer-re/Rikugan --skill vuln-auditgit clone --depth 1 https://github.com/buzzer-re/RikuganWrote 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/buzzer-re/rikugan/vuln-audit)<a href="https://agentmods.dev/skills/buzzer-re/rikugan/vuln-audit"><img src="https://agentmods.dev/badge/skills/buzzer-re/rikugan/vuln-audit/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/buzzer-re/rikugan/vuln-audit"><img src="https://agentmods.dev/badge/skills/buzzer-re/rikugan/vuln-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00019 | $0.00704 |
| Opus 5.5 | $0.00008 | $0.00282 |
| Sonnet 5.5 | $0.00004 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
Vulnerability Audit 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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task: Security Vulnerability Audit. You are auditing a binary for exploitable vulnerabilities.
Approach
Systematic, evidence-based. Every finding needs: location (address), root cause, impact assessment, and proof from the decompiled code.
Phase 1: Attack Surface Mapping
list_imports— identify dangerous APIs:- Memory: memcpy, memmove, strcpy, strncpy, sprintf, vsprintf, gets
- Format strings: printf, fprintf, syslog, snprintf with user-controlled format
- Heap: malloc, free, realloc (use-after-free, double-free)
- File I/O: fopen, CreateFile, read, write (path traversal)
- Network: recv, recvfrom, WSARecv (remote input)
- Command: system, popen, execve, ShellExecute (command injection)
list_exports— identify entry points accessible to attackerssearch_strings— look for format strings, SQL patterns, command templates
Phase 2: Input Tracing
For each dangerous API found:
xrefs_toon the import — find all call sitesdecompile_functionon each caller- Trace backwards: where does the buffer/size/format argument come from?
- Is it user-controlled? (network input, file input, IPC, environment)
- Are there bounds checks between input and dangerous API?
Phase 3: Vulnerability Classes
Buffer Overflow (Stack)
- Fixed-size stack buffer + unbounded copy (strcpy, sprintf, gets)
- Size parameter larger than destination buffer
- Off-by-one in loop bounds writing to stack buffer
Buffer Overflow (Heap)
- malloc(user_size) without upper bound check
- memcpy into heap buffer with unchecked length
- Integer overflow in size calculation → small allocation, large copy
Format String
- printf(user_input) without format specifier
- syslog, fprintf with attacker-controlled first argument
Integer Overflow/Underflow
- Arithmetic on user-controlled sizes before allocation
- Signed/unsigned comparison mismatches in bounds checks
- Multiplication overflow in array index calculations
Use-After-Free
- free() followed by continued use of the pointer
- Dangling pointers in linked structures after partial cleanup
- Race conditions in multi-threaded free/use paths
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.
- 1mo ago First seen · 81 lines · 19 tokens per session scan A 047a0c92a29d
Vulnerability Audit is a skill published in the GitHub repository buzzer-re/Rikugan (694 stars, last pushed 14d ago), licensed MIT. It adds 19 tokens to every session and 704 once invoked, about $0.0001 per session on Opus 5.5. 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
security-audit
Smart contract security audit assistant powered by Solodit API. Search 50,000+ vulnerabilities, fetch contracts from 40+ chains, run static analysis, generate PoC exploits and audit reports.
edgeone-clawscan
The first security skill to install after setting up OpenClaw — powered by Tencent Zhuque Lab. Works like an antivirus for your AI environment: audits installed skills, scans skills before installation, and performs a full OpenClaw security health check to prevent data leaks and privacy risks. Backed by Tencent Zhuque…
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
security-audit
Security audit + fix — scans for hardcoded secrets, injection vectors, path traversal, input validation gaps, then implements all fixes.
security-review
Scan code changes for security vulnerabilities using STRIDE threat modeling, validate findings for exploitability, and output structured results for downstream patch generation. Supports PR review, scheduled scans, and full repository audits.
security-audit
OWASP-style security audit focused on real exploits, not abstract advice. Invoke before shipping anything that handles user input, secrets, or external I/O.