SKILLEMALL.ai

BB ctf-reverse

Provides reverse engineering techniques for CTF challenges. Use when analyzing binaries, game clients, obfuscated code, esoteric languages, custom VMs, anti-debugging, anti-analysis bypass, WASM, .NET, APK (including Flutter/Dart AOT with Blutter), HarmonyOS HAP/ABC, Python bytecode, Go/Rust/Swift/Kotlin binaries, VMProtect/Themida, Ghidra, GDB, radare2, Frida, angr, Qiling, Triton, binary diffing, macOS/iOS Mach-O, embedded firmware, kernel modules, game engines, or extracting flags from compiled executables.

ClawHub Agent Skills author: gandli v1.0.0 MIT-0 15 files body ≈ 9 221 tokens Open the sourceclawhub.ai analyzed 2 d ago

As a process B 70/100 · Nearly there — weak spots: when it triggers, execution cost, running it twice

AnalyzerGitHubSoftware developmenttype and topics are labelled automatically from the skill text
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
82
Quality 40%
78
Run on models
none yet
Process rating
B
70/100
Nearly there
Progress reporting w 2
0
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 14

✓ No critical or high findings

Medium and low: 14
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Write Edit Glob Grep Task WebFetch WebSearch
  • low Risky intent intent-offensive-security languages-compiled.md:197
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    **Pattern (see-two):** A Go-compiled C2 client has a UUID embedded via `-ldflags -X`. The C2 server uses mTLS for authentication. To enumerate other clients and their files, patch the UUID to register
  • low Risky intent intent-offensive-security languages-compiled.md:202
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    3. Register with the C2 server using the patched binary (mTLS certs are embedded or in distfiles)
  • low Secrets in code secret-high-entropy-token languages-compiled.md:340
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    swift demangle 's14M…_tF'
    quoted
  • low Risky intent intent-offensive-security patterns-ctf.md:19
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - [Hash-Resolved Imports / No-Import Ransomware (BSidesSF 2026)](#hash…026)
  • low Risky intent intent-offensive-security patterns-ctf.md:521
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ## Hash-Resolved Imports / No-Import Ransomware (BSidesSF 2026)
  • low Risky intent intent-offensive-security patterns-ctf.md:536
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    // hook_crypto.c — captures AES key used by the ransomware
  • low Risky intent intent-offensive-security patterns-ctf.md:561
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    # Run in Docker container (ransomware may be destructive!)
  • low Risky intent intent-offensive-security patterns-ctf.md:563
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    bash -c "LD_PRELOAD=./hook.so ./ransomware; xxd /tmp/aes_key.bin"
    quoted
  • low Secrets in code secret-high-entropy-token platforms.md:118
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    swift demangle 's14M…_tF'
    quoted
  • low Risky intent intent-offensive-security SKILL.md:49
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - [patterns-ctf.md](patterns-ctf.md) - Competition-specific patterns (Part 1): hidden emulator opcodes, LD_PRELOAD key extraction, SPN static extraction, image XOR smoothness, byte-at-a-time cipher, m
  • low Risky intent intent-offensive-security SKILL.md:367
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ## Hash-Resolved Imports / No-Import Ransomware (BSidesSF 2026)
  • low Risky intent intent-offensive-security SKILL.md:369
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    **Pattern:** Binary with zero visible imports resolves APIs via symbol name hashing at runtime. Skip the hash reversing — hook OpenSSL functions via `LD_PRELOAD` in Docker to capture AES keys directly
    detector

A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 9221 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 70/100

  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 6 mutating operations with no state check
  • 40Execution cost. Instruction body is 9221 tokens: crowds the task out of the window
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Failures and branches. 8 branches
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 49 steps
  • 100Consistency. Name and required fields are in place
  • low 87 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +2Single-language instructions
  • +3Description length 515: enough signal without eating the budget
  • +4Structure: 95 headings
  • +3Step-by-step instructions: 49 items
  • +3Output format is stated explicitly
  • +4Has examples (10 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: suspicious
This is a CTF reverse-engineering reference, but it includes under-scoped operational instructions for impersonation, bypasses, data retrieval, and cyber-physical actions that users should review carefully before installing.
LLM: suspicious (high) · VirusTotal: · 29 May 2026