Skills/ClawHub/ctf-pwn-exploit

ctf-pwn-exploit@1.0.0

CAUTION· static only

Publisher claims: "PWN二进制利用助手：栈溢出/堆利用/格式化字符串/ROP/ret2libc/shellcode 的攻击流程与利用脚本开发。遇到 pwn、溢出、ROP、shellcode、格式化字符串、GOT、canary、堆块利用类题目时使用。" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher yxy050208 · publishing for 73 daysInstalls 495Last detonated 13 h ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-08 and scored it 67/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe to network utility. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

LOW
Prompt injectionreferences/ctf-pwn/field-notes.md:127 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file…l array, enabling stack return address overwrite. Leak stack address via hidden developer mode, encode shellcode as block IDs. See [advanced-exploits-3.md](advanced-exploits-…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionreferences/ctf-pwn/advanced-exploits-3.md:362 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file2. Enable developer mode (hidden konami-code input sequence) to leak level data stack addressFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Cipher/encoding referencereferences/ctf-pwn/format-string.md:638 · Cipher/encoding reference — may contain obfuscated instructions · informational: not an instruction file# rot13('%2$x|%3$x') produces encoded string; after binary's rot13, printf sees '%2$x|%3$x'Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
LOW
Authorization escalation languagereferences/ctf-pwn/field-notes.md:127 · Authorization escalation language · informational: not an instruction file · informational: not an instruction file…l array, enabling stack return address overwrite. Leak stack address via hidden developer mode, encode shellcode as block IDs. See [advanced-exploits-3.md](advanced-exploits-…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injection attemptreferences/ctf-pwn/advanced-exploits.md:93 · Prompt injection attempt — model control tokens · informational: not an instruction file · informational: not an instruction file4. Write ROP chain into entries 17-22: `[canary] [rbp] [ret] [pop_rdi] [/bin/sh] [system]`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Pipe to network utilityreferences/ctf-pwn/SKILL.md:104 · Pipe to network utility — potential reverse shellbash -c '{ echo "cmd1"; echo "cmd2"; sleep 1; } | nc host port'Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Context shift attemptreferences/ctf-pwn/advanced-exploits-3.md:362 · Context shift attempt — trying to change operational mode · informational: not an instruction file · informational: not an instruction file2. Enable developer mode (hidden konami-code input sequence) to leak level data stack addressFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Cipher/encoding referencereferences/ctf-pwn/format-string.md:623 · Cipher/encoding reference — may contain obfuscated instructions · informational: not an instruction file2. ROT13 is self-inverse: `rot13(rot13(x)) = x`Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
LOW
Cipher/encoding referencereferences/ctf-pwn/format-string.md:632 · Cipher/encoding reference — may contain obfuscated instructions · informational: not an instruction filedef rot13(s):Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
LOW
Cipher/encoding referencereferences/ctf-pwn/format-string.md:639 · Cipher/encoding reference — may contain obfuscated instructions · informational: not an instruction fileio.sendline(rot13('%2$x|%3$x').encode())Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
LOW
Authorization escalation languagereferences/ctf-pwn/advanced-exploits-3.md:372 · Authorization escalation language · informational: not an instruction file · informational: not an instruction fileleaked_addr = 0x7ffd3de47d70 # From developer mode leakFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languagereferences/ctf-pwn/advanced-exploits-3.md:362 · Authorization escalation language · informational: not an instruction file · informational: not an instruction file2. Enable developer mode (hidden konami-code input sequence) to leak level data stack addressFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionreferences/ctf-pwn/advanced-exploits-3.md:372 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction fileleaked_addr = 0x7ffd3de47d70 # From developer mode leakFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionreferences/ctf-pwn/format-string.md:499 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file · informational: not an instruction file…on window to an empty range. Format specifiers like `%n` placed beyond byte 255 bypass the filter entirely. **Vulnerable code pattern:** ```c void filter(char *input) { int…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languagereferences/ctf-pwn/kernel-bypass.md:240 · Authorization escalation language · informational: not an instruction file · informational: not an instruction file- Comment out `exec su -l ctf` (or similar) to keep root privilegesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languagereferences/ctf-pwn/field-notes.md:184 · Authorization escalation language · informational: not an instruction file · informational: not an instruction fileLook for `cuse_lowlevel_main()` / `fuse_main()`, backdoor write handlers with command parsing. Exploit to `chmod /etc/passwd` then modify for root access. See [sandbox-escape.md](sandbox-escape.md).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languagereferences/ctf-pwn/kernel-bypass.md:145 · Authorization escalation language · informational: not an instruction file · informational: not an instruction file…age table, the credentials are already committed. The SIGSEGV handler runs with root privileges. ### Method 3: modprobe_path via ROP Instead of returning to userland, overw…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈5,635 tok
2 files · 21 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

13 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim yxy050208: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Pipe to network utility≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim yxy050208Propose a patch to the maintainer