Skills/PyPI/poe2-mcp

poe2-mcp@1.0.15

CAUTION· not started

Publisher claims: "AI-powered Path of Exile 2 build optimization MCP server" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher hivemindoverlord · publishing for 333 daysInstalls 708Last detonated 1 h ago
What would fix thisWatchDispute verdict

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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso poe.ninja, pathofexile.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 under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx poe2-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 2026-11-14 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Auto-update or dynamic fetch configuration; Access to sensitive file paths; Hidden zero-width characters detected. 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
Python subprocess execution detectedsrc/data/update_manager.py:89 · Python subprocess execution detectedout = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/data/update_manager.py:16 · Auto-update or dynamic fetch configuration — agent may load new code at runtime* ``POE2_MCP_AUTO_UPDATE=1`` -> ``auto`` : permission granted ahead of time;Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcp_server.py:2647 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Or manually update POESESSID in your .env file and restart the server.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionsrc/mcp_server.py:1072 · File type combined with upload action — agent may exfiltrate local data files"skill_gems_v2.json (~1,249 spells, post-#119). "Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/knowledge/poe2_mechanics.py:1350 · Process kill command — agent can terminate processes"How do I generate Endurance Charges?": "Skills (Enduring Cry), on-kill effects, passives, or items.",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Hidden zero-width characters detectedsrc/pob/importer.py:122 · Hidden zero-width characters detected — may conceal contentroot = ET.fromstring(xml_str.lstrip("").strip())Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Access to sensitive file pathssrc/config.py:155 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file=str(BASE_DIR / ".env"), # Use absolute pathFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionsrc/mcp_server.py:746 · File type combined with upload action — agent may exfiltrate local data files…rt a Path of Building build. Accepts a local file path (most reliable — a saved .xml build or a .txt containing the share code, auto-detected), raw uncompressed PoB XML, or an inline base64 share code. Provide exactly one of the three inpu…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathssrc/config.py:139 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesf"not survive a restart. For persistence, add it to .env: "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsrc/knowledge/poe2_mechanics.py:1421 · Process kill command — agent can terminate processes"How do I generate Frenzy Charges?": "Skills, on-kill effects, charms (like Valako's Roar), or passives.",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/knowledge/poe2_mechanics.py:1392 · Process kill command — agent can terminate processes1. Generate charges through skills, passives, or on-kill effectsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Hex-encoded string detectedsrc/data/fresh_data_provider.py:36 · Hex-encoded string detected — may contain obfuscated payloadsbbbb = self.content.find(b"\xbb\xbb\xbb\xbb\xbb\xbb\xbb\xbb")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Auto-update or dynamic fetch configurationsrc/launcher_helpers.py:34 · Auto-update or dynamic fetch configuration — agent may load new code at runtime- POE2_MCP_AUTO_UPDATE=1 fast-forward merge if possible (Option B)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/launcher_helpers.py:55 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/mcp_server.py:4991 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesresponse += "**Saving to .env file...**\n"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 pathssrc/config.py:49 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(Claude Desktop: C:\\WINDOWS\\system32). A .env override likeFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/api/trade_api.py:51 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Or see .env.example for manual cookie extraction instructions."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Hex-encoded string detectedsrc/parsers/datc64_parser.py:19 · Hex-encoded string detected — may contain obfuscated payloadsDAT_MAGIC_NUMBER = b"\xbb\xbb\xbb\xbb\xbb\xbb\xbb\xbb"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Auto-update or dynamic fetch configurationsrc/launcher_helpers.py:109 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeauto_update = os.environ.get("POE2_MCP_AUTO_UPDATE") == "1"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/ai/query_handler.py:43 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn "AI features are not enabled. Please set ANTHROPIC_API_KEY in your .env file."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsrc/knowledge/poe2_mechanics.py:435 · Process kill command — agent can terminate processes"Shatter frozen enemies on kill for on-death immunity",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/mcp_server.py:4990 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Save to .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_server.py:4923 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file = base_dir / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/launcher_helpers.py:114 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeprint_info("Set POE2_MCP_AUTO_UPDATE=1 to enable automatic fast-forward updates.")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/config.py:115 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Set via environment variables (.env file) for persistence:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/data/data_distributor.py:209 · Auto-update or dynamic fetch configuration — agent may load new code at runtimef"set POE2_MCP_AUTO_UPDATE=1 or use check_for_updates(apply=true). "Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcp_server.py:2610 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"5. Add to .env: POESESSID=your_cookie_value\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsrc/knowledge/poe2_mechanics.py:1321 · Process kill command — agent can terminate processes1. Generate charges through skills, passives, or on-kill effectsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈49 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

No advisories in OSV for poe2-mcp@1.0.15 as of 1 h ago. This is the package itself, not its dependencies.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim hivemindoverlord: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  3. 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.
  4. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  5. Hex-encoded string detected≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  6. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim hivemindoverlordPropose a patch to the maintainer