Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/allsmog/pwn-claude-pluginnpx agentmods add skills/allsmog/pwn-claude-plugin/reconnaissanceWrote 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/allsmog/pwn-claude-plugin/reconnaissance)<a href="https://agentmods.dev/skills/allsmog/pwn-claude-plugin/reconnaissance"><img src="https://agentmods.dev/badge/skills/allsmog/pwn-claude-plugin/reconnaissance/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/allsmog/pwn-claude-plugin/reconnaissance"><img src="https://agentmods.dev/badge/skills/allsmog/pwn-claude-plugin/reconnaissance.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 | $0.00068 | $0.01353 |
| Opus 5.5 | $0.00027 | $0.00541 |
| Sonnet 5.5 | $0.00014 | $0.00271 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
PWN Reconnaissance 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 2mo 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PWN Reconnaissance
Overview
The reconnaissance phase gathers critical information about a target binary before exploitation. This includes identifying architecture, protections, interesting strings, symbols, and potential libc version.
Reconnaissance Checklist
- File type and architecture identification
- Security protections (checksec)
- Interesting strings extraction
- Symbol table analysis
- Libc identification (if applicable)
- Seccomp filter detection
Step 1: File Identification
Identify the binary type and architecture:
file ./binary
Expected output interpretation:
| Output Contains | Meaning |
|---|---|
| ELF 64-bit LSB executable | x86_64 architecture |
| ELF 32-bit LSB executable | x86 (i386) architecture |
| dynamically linked | Uses shared libraries (libc) |
| statically linked | Self-contained, no libc exploits |
| not stripped | Contains debug symbols |
| stripped | No debug symbols |
Step 2: Security Protections
Run checksec to identify protections:
checksec --file=./binary
Or via pwntools:
from pwn import *
elf = ELF('./binary')
print(elf.checksec())
Protection Analysis
| Protection | Enabled | Exploitation Impact |
|---|---|---|
| RELRO | Partial | GOT overwrite possible |
| RELRO | Full | No GOT overwrite, use other primitives |
| Stack Canary | Yes | Must leak or bypass canary |
| NX | Yes | No shellcode on stack, use ROP/ret2libc |
| PIE | Yes | Must leak binary base address |
| FORTIFY | Yes | Some unsafe functions hardened |
Step 3: Strings Extraction
Find interesting strings:
strings -n 8 ./binary | grep -iE '(flag|password|secret|admin|shell|bin/sh|/bin)'
Look for:
- Format string specifiers (
%s,%x,%n) - Function names (
system,execve) - File paths (
/bin/sh,/flag) - Potential passwords or keys
Step 4: Symbol Analysis
Extract symbols if not stripped:
nm ./binary | grep -E ' [TtWw] ' | head -30
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 213 lines · 68 tokens per session scan A b1cb201d0b9a
PWN Reconnaissance is a skill published in the GitHub repository allsmog/pwn-claude-plugin (2 stars, last pushed 8mo ago), licensed MIT. It adds 68 tokens to every session and 1,353 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
bypassing-binary-exploitation-mitigations
Methodology for identifying and defeating common binary hardening mitigations during authorized exploitation — ASLR, PIE, stack canaries, NX/DEP, and RELRO — by leaking addresses, brute-forcing entropy, abusing forked-process behavior, and selecting the right code-reuse primitive for the protections in place.
exploiting-arbitrary-write-to-execution
Methodology for converting an arbitrary-write (write-what-where) or write-anything-anywhere primitive into code execution during authorized engagements, covering target selection among GOT/PLT entries, .finiarray/.dtors, mallochook/freehook, the atexit/exitfuncs handler list, and printfarginfotable, plus how…
exploiting-format-string-vulnerabilities
Methodology for exploiting format string bugs where attacker-controlled data reaches the format argument of printf-family functions, enabling stack/memory disclosure (info leaks for ASLR/PIE/canary defeat) and arbitrary write primitives (%n) to hijack control flow via GOT/.finiarray overwrites.
exploiting-glibc-heap-vulnerabilities
Methodology for exploiting glibc ptmalloc2 heap vulnerabilities during authorized engagements — use-after-free, double-free, heap overflow, and bin-based attacks (tcache poisoning, fast-bin dup, unsorted/large-bin) — including modern mitigations (tcache key, safe-linking, hook removal) and how to obtain leaks and…
exploiting-integer-overflow-vulnerabilities
Methodology for finding and exploiting integer overflow, underflow, truncation, and signedness bugs in native code during authorized engagements, focusing on how wrapped arithmetic in size/length calculations leads to undersized allocations, oversized copies, length-check bypasses, and downstream heap/stack overflows.
exploiting-linux-kernel-vulnerabilities
Methodology for discovering and exploiting Linux kernel memory-corruption vulnerabilities (UAF, OOB read/write, race/TOCTOU, type confusion) during authorized engagements, covering reachability analysis, building stable read/write primitives from a single bug, defeating KASLR/SMEP/SMAP/KPTI, slab/buddy heap grooming…