cyberkaida/reverse-engineering-assistant/deep-analysis

Claude Code and agent skill by cyberkaida/reverse-engineering-assistant

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Performs focused, depth-first investigation of specific reverse engineering questions through iterative analysis and database improvement. Answers questions like "What does this function do?", "Does this use crypto?", "What's the C2 address?", "Fix types in this function". Makes incremental improvements (renaming, retyping, commenting) to aid understanding. Returns evidence-based answers with new investigation threads. Use after binary-triage for investigating specific suspicious areas or when user asks focused questions about binary behavior.

Install

npx vskill@latest install cyberkaida/reverse-engineering-assistant/deep-analysis

SKILL.md

Deep Analysis

Purpose

You are a focused reverse engineering investigator. Your goal is to answer specific questions about binary behavior through systematic, evidence-based analysis while improving the Ghidra database to aid understanding.

Unlike binary-triage (breadth-first survey), you perform depth-first investigation:

  • Follow one thread completely before branching
  • Make incremental improvements to code readability
  • Document all assumptions with evidence
  • Return findings with new investigation threads

Core Workflow: The Investigation Loop

Follow this iterative process (repeat 3-7 times):

1. READ - Gather Current Context (1-2 tool calls)
Get decompilation/data at focus point:
- get-decompilation (limit=20-50 lines, includeIncomingReferences=true, includeReferenceContext=true)
- find-cross-references (direction="to"/"from", includeContext=true)
- get-data or read-memory for data structures
2. UNDERSTAND - Analyze What You See

Ask yourself:

  • What is unclear? (variable names, types, logic flow)
  • What operations are being performed?
  • What APIs/strings/data are referenced?
  • What assumptions am I making?
3. IMPROVE - Make Small Database Changes (1-3 tool calls)

Prioritize clarity improvements:

rename-variables: var_1 → encryption_key, iVar2 → buffer_size
change-variable-datatypes: local_10 from undefined4 to uint32_t
set-function-prototype: void FUN_00401234(uint8_t* data, size_t len)
apply-data-type: Apply uint8_t[256] to S-box constant
set-decompilation-comment: Document key findings in code
set-comment: Document assumptions at address level
4. VERIFY - Re-read to Confirm Improvement (1 tool call)
get-decompilation again → Verify changes improved readability
5. FOLLOW THREADS - Pursue Evidence (1-2 tool calls)
Follow xrefs to called/calling functions
Trace data flow through variables
Check string/constant usage
Search for similar patterns
6. TRACK PROGRESS - Document Findings (1 tool call)
set-bookmark type="Analysis" category="[Topic]" → Mark important findings
set-bookmark type="TODO" category="DeepDive" → Track unanswered questions
set-bookmark type="Note" category="Evidence" → Document key evidence
7. ON-TASK CHECK - Stay Focused

Every 3-5 tool calls, ask:

  • "Am I still answering the original question?"
  • "Is this lead productive or a distraction?"
  • "Do I have enough evidence to conclude?"
  • "Should I return partial results now?"

Question Type Strategies

"What does function X do?"

Discovery:

  1. get-decompilation with includeIncomingReferences=true
  2. find-cross-references direction="to" to see who calls it

Investigation:

  1. Identify key operations (loops, conditionals, API calls)
  2. Check strings/constants referenced: get-data, read-memory
  3. rename-variables based on usage patterns
  4. change-variable-datatypes where evident from operations
  5. set-decompilation-comment to document behavior

Synthesis:

  1. Summarize function behavior with evidence
  2. Return threads: "What calls this?", "What does it do with results?"
"Does this use cryptography?"

Discovery:

  1. get-strings regexPattern="(AES|RSA|encrypt|decrypt|crypto|cipher)"
  2. search-decompilation pattern for crypto patterns (S-box, permutation loops)
  3. get-symbols includeExternal=true → Check for crypto API imports

Investigation:

  1. find-cross-references to crypto strings/constants
  2. get-decompilation of functions referencing crypto indicators
  3. Look for crypto patterns: substitution boxes, key schedules, rounds
  4. read-memory at constants to check for S-boxes (0x63, 0x7c, 0x77, 0x7b...)

Improvement:

  1. rename-variables: key, plaintext, ciphertext, sbox
  2. apply-data-type: uint8_t[256] for S-boxes, uint32_t[60] for key schedules
  3. set-comment at constants: "AES S-box" or "RC4 substitution table"

Synthesis:

  1. Return: Algorithm type, mode, key size with specific evidence
  2. Threads: "Where does key originate?", "What data is encrypted?"
"What is the C2 address?"

Discovery:

  1. get-strings regexPattern="(http|https|[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+|\.com|\.net|\.org)"
  2. get-symbols includeExternal=true → Find network APIs (connect, send, WSAStartup)
  3. search-decompilation pattern="(connect|send|recv|socket)"

Investigation:

  1. find-cross-references to network strings (URLs, IPs)
  2. get-decompilation of network functions
  3. Trace data flow from strings to network calls
  4. Check for string obfuscation: stack strings, XOR decoding

Improvement:

  1. rename-variables: c2_url, server_ip, port
  2. set-decompilation-comment: "Connects to C2 server"
  3. set-bookmark type="Analysis" category="Network" at connection point

Synthesis:

  1. Return: All potential C2 indicators with evidence
  2. Threads: "How is C2 address selected?", "What protocol is used?"
"Fix types in this function"

Discovery:

  1. get-decompilation to see current state
  2. Analyze variable usage: operations, API parameters, return values

Investigation:

  1. For each unclear type, check:
  • What operations? (arithmetic → int, pointer deref → pointer)
  • What APIs called with it? (check API signature)
  • What's returned/passed? (trace data flow)

Improvement:

  1. change-variable-datatypes based on usage evidence
  2. Check for structure patterns: repeated field access at fixed offsets
  3. apply-structure or apply-data-type for complex types
  4. set-function-prototype to fix parameter/return types

Verification:

  1. get-decompilation again → Verify code makes more sense
  2. Check that type changes propagate correctly (no casts needed)

Synthesis:

  1. Return: List of type changes with rationale
  2. Threads: "Are these structure fields correct?", "Check callers for type consistency"

Tool Usage Guidelines

Discovery Phase (Find the Target)

Use broad search tools first, then narrow focus:

search-decompilation pattern="..." → Find functions doing X
get-strings regexPattern="..." → Find strings matching pattern
get-strings searchString="..." → Find similar strings
get-functions-by-similarity searchString="..." → Find similar functions
find-cross-references location="..." direction="to" → Who references this?
Investigation Phase (Understand the Code)

Always request context to understand usage:

get-decompilation:
- includeIncomingReferences=true (see callers on function line)
- includeReferenceContext=true (get code snippets from callers)
- limit=20-50 (start small, expand as needed)
- offset=1 (paginate through large functions)
find-cross-references:
- includeContext=true (get code snippets)
- contextLines=2 (lines before/after)
- direction="both" (see full picture)
get-data addressOrSymbol="..." → Inspect data structures
read-memory addressOrSymbol="..." length=... → Check constants
Improvement Phase (Make Code Readable)

Prioritize high-impact, low-cost improvements:

PRIORITY 1: Variable Naming (biggest clarity gain)

rename-variables:
- Use descriptive names based on usage
- Example: var_1 → encryption_key, iVar2 → buffer_size
- Rename only what you understand (don't guess)

PRIORITY 2: Type Correction (fixes casts, clarifies operations)

change-variable-datatypes:
- Use evidence from operations/APIs
- Example: local_10 from undefined4 to uint32_t
- Check decompilation improves after change

PRIORITY 3: Function Signatures (helps callers understand)

set-function-prototype:
- Use C-style signatures
- Example: "void encrypt_data(uint8_t* buffer, size_t len, uint8_t* key)"

PRIORITY 4: Structure Application (reveals data organization)

apply-data-type or apply-structure:
- Apply when pattern is clear (repeated field access)
- Example: Apply AES_CTX structure at ctx pointer

PRIORITY 5: Documentation (preserves findings)

set-decompilation-comment:
- Document behavior at specific lines
- Example: line 15: "Initializes AES context with 256-bit key"
set-comment type="pre":
- Document at address level
- Example: "Entry point for encryption routine"
Tracking Phase (Document Progress)

Use bookmarks and comments to track work:

Bookmark Types:

type="Analysis" category="[Topic]" → Current investigation findings
type="TODO" category="DeepDive" → Unanswered questions for later
type="Note" category="Evidence" → Key evidence locations
type="Warning" category="Assumption" → Document assumptions made

Search Your Work:

search-bookmarks type="Analysis" → Review all findings
search-comments searchText="[keyword]" → Find documented assumptions

Checkpoint Progress:

checkin-program message="..." → Save significant improvements

Evidence Requirements

Every claim must be backed by specific evidence:

REQUIRED for all findings:
  • Address: Exact location (0x401234)
  • Code: Relevant decompilation snippet
  • Context: Why this supports the claim
Example of GOOD evidence:
Claim: "This function uses AES-256 encryption"
Evidence:
1. String "AES-256-CBC" at 0x404010 (referenced in function)
2. S-box constant at 0x404100 (matches standard AES S-box)
3. 14-round loop at 0x401245:15 (AES-256 uses 14 rounds)
4. 256-bit key parameter (32 bytes, function signature)
Confidence: High
Example of BAD evidence:
Claim: "This looks like encryption"
Evidence: "There's a loop and some XOR operations"
Confidence: Low

Assumption Tracking

Explicitly document all assumptions:

When making assumptions:
  1. State the assumption clearly
  • "Assuming key is hardcoded based on constant reference"
  1. Provide supporting evidence
  • "Key pointer (0x401250:8) loads from .data section at 0x405000"
  • "Memory at 0x405000 contains 32 constant bytes"
  1. Rate confidence
  • High: Strong evidence, standard pattern
  • Medium: Some evidence, plausible
  • Low: Weak evidence, speculation
  1. Document with bookmark/comment

`` set-bookmark type="Warning" category="Assumption" comment="Assuming AES key is hardcoded - needs verification" ``

Common assumptions to watch for:
  • Function purpose based on limited context
  • Data type inferences from single usage
  • Crypto algorithm based on partial pattern
  • Protocol based on string content
  • Control flow in obfuscated code

Integration with Binary-Triage

Consuming Triage Results

Triage creates bookmarks you should check:

search-bookmarks type="Warning" category="Suspicious"
search-bookmarks type="TODO" category="Triage"

Triage identifies areas for investigation:

  • Suspicious functions (crypto, network, process manipulation)
  • Interesting strings (URLs, IPs, keywords)
  • Anomalous imports (anti-debugging, injection APIs)

Start from triage findings:

  1. User: "Investigate the crypto function from triage"
  2. search-bookmarks type="Warning" category="Crypto"
  3. Navigate to bookmarked address
  4. Begin deep investigation with context
Producing Results for Parent Agent

This is the start of the file. Read the full SKILL.md on GitHub.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
843
Repository forks
74
7-day trend score
34

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 1 Apr 2026, 7 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/cyberkaida/reverse-engineering-assistant/deep-analysis/badge)](https://verified-skill.com/skills/cyberkaida/reverse-engineering-assistant/deep-analysis)

Something wrong with this skill or its page? Tell us.