SKILLEMALL.ai
GitHub ↗ RU Sign in

BC binary-analysis

Analyze unknown binary files through a deterministic CLI that wraps Ghidra's static-analysis engine. Use when you need to inspect a PE, ELF, or Mach-O file — triage suspicious binaries, map imported APIs, decompile functions, trace call paths, or produce structured evidence reports. Do not use for runtime analysis (debugging, dynamic tracing, sandbox execution), for modifying or patching binaries, or for binaries you already know everything about. The skill owns planning, hypothesis formation, and evidence synthesis; the CLI owns all deterministic operations.

magnus919/agent-skills Agent Skills author: magnus919 MIT 80 files · 66 scripts body ≈ 3 521 tokens Open the sourcegithub.com↗ analyzed 27 h ago

Analyze unknown binary files through a deterministic CLI that wraps Ghidra's static-analysis engine.

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting

AnalyzerData and analyticsAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
93/100
safety, quality, tests
Safety 60%
93
Quality 40%
93
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 7

    ✓ No critical or high findings

    Medium and low: 7
    • low Risky intent intent-offensive-security references/evidence-and-confidence.md:132
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      this is a credential harvesting tool."
    • low Risky intent intent-offensive-security references/evidence-and-confidence.md:248
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      **Wrong:** "This is a ransomware binary."
      quoted
    • low Risky intent intent-offensive-security references/evidence-and-confidence.md:253
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ransomware behavior, but ransomware cannot be confirmed without dynamic
    • low Risky intent intent-offensive-security references/security.md:145
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | cryptography | CryptEncrypt, CryptDecrypt, AES/RC4 constants | Data protection, TLS, DRM | Ransomware, credential encryption, C2 obfuscation |
    • low Risky intent intent-offensive-security references/security.md:150
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | service-management | CreateService, StartService, OpenSCManager | Installers, service apps | Persistence, privilege escalation |
    • low Risky intent intent-offensive-security references/triage-workflow.md:277
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      CreateRemoteThread chain) and possible credential harvesting (confidence:
    • low Dangerous commands cmd-privilege scripts/binary_analysis/rules/capabilities.py:524
      Privilege escalation / world-writable permissions (string literal in code, not executed)
      "setuid",
      code literal

    Files scanned: 63. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 57/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 70Failures and branches. 4 branches
    • 100Steps. 30 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3521 tokens
    • 100Running it twice. Mutating operations check current state
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 10 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
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 565: enough signal without eating the budget
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 30 items
    • +4Has examples (11 code blocks)
    • +4Reference files are cited in the instructions (11 of 11)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.