Skills/PyPI/reversecore-mcp

reversecore-mcp@3.1.0

CAUTION· not started

Publisher claims: "A security-first MCP server that empowers AI agents to perform automated reverse engineering, malware analysis, forensics, vulnerability research, and SAST — powered by Radare2, YARA, LIEF, Capstone, and more." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher sjkim1127 · publishing for 6 daysInstalls 626Last detonated 19 min ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
REPORT_SMTP_PASSWORDConfiguration, not credentials: ALLOWED_ORIGINS, CLAUDE_CONFIG_DIR, R2GHIDRA_DB_PATH, REPORT_QUICK_CONTACTS, REPORT_SENDER_NAME, REPORT_SMTP_PORT, REPORT_SMTP_SERVER, REPORT_SMTP_USE_TLS, REPORT_SMTP_USERNAME, REVERSECORE_EVIDENCE_CACHE_DIR, REVERSECORE_RATE_LIMIT_STRICT, REVERSECORE_REDIS_URL, REVERSECORE_UPLOAD_ENABLED, REVERSECORE_WORKSPACE
Where it talks to
no vendor host named in the codeAlso evil.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names evil.com as well as its own vendor. The guard injects REPORT_SMTP_PASSWORD only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx reversecore-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-16 and scored it 71/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collapsed <details> block carrying instructions; Collapsed <details> block carrying instructions; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commandreversecore_mcp/prompts/malware.py:193 · Process kill command — agent can terminate processesWhere does this fit in the cyber kill chain?Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:789 · Collapsed <details> block carrying instructions<summary>🐧 Linux</summary> ```json { "mcpServers": { "reversecore": { "command": "docker", "args": [ "run", "-i", "--rm", "-v", "/home/YOUR_USERNAME/samples:/aFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:767 · Collapsed <details> block carrying instructions<summary>🍎 macOS</summary> ```json { "mcpServers": { "reversecore": { "command": "docker", "args": [ "run", "-i", "--rm", "-v", "/Users/YOUR_USERNAME/samples:/Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsreversecore_mcp/core/config.py:61 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file=".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsreversecore_mcp/prompts/security.py:98 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Look for configuration files (/etc/shadow, /etc/passwd, .conf).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:1661 · Collapsed <details> block carrying instructions<summary><b>Timeout error (RCMCP-E002 / RCMCP-E200)</b></summary> Analysis exceeded the configured timeout. **Solution:** Increase the timeout: ```bash export RFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Agent configured for autonomous execution without human approvalreversecore_mcp/core/next_tool_hints.py:721 · Agent configured for autonomous execution without human approval"Autonomous hunt completed with fuzzing disabled and no confirmed exploits. "Fix: Declare and request only the permissions the task needs.
AST02
HIGH
Collapsed <details> block carrying instructionsREADME.md:1692 · Collapsed <details> block carrying instructions<summary><b>Docker container won't start on Apple Silicon</b></summary> Make sure you're using the ARM64 profile: ```bash docker compose --profile arm64 up -d `Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:811 · Collapsed <details> block carrying instructions<summary>🪟 Windows</summary> ```json { "mcpServers": { "reversecore": { "command": "docker", "args": [ "run", "-i", "--rm", "-v", "C:/samples:/app/workspace", Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandreversecore_mcp/core/execution.py:485 · Process kill command — agent can terminate processeslogger.error(f"Failed to kill process {process.pid}: {e}")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈90 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Agent configured for autonomous execution without human approval≈ +9 on the totalDeclare and request only the permissions the task needs.
  2. Unclaimed publisher≈ +8 on the totalClaim sjkim1127: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim sjkim1127Propose a patch to the maintainer