Skills/npm/arc-security-mcp

arc-security-mcp@0.5.1

CAUTION

Publisher claims: "Scan AI agent skills for 25 attack classes + runtime monitoring. 1,316+ findings." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher arcself · joined 0 days agoInstalls 0Last detonated 3 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-05 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; References a credential file in the home directory; Agent configured for autonomous execution without human approval. 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
0.1sprocessexec /usr/bin/date
0.1sprocessexec /usr/bin/timeout
0.1sprocessexec /usr/bin/which
0.1sclaimedno tools/list reply (exit 0)
0.1sprocessscript backend runs setup only

Static findings

CRITICAL
Pipe-to-shell patternserver.py:787 · Pipe-to-shell pattern — downloads and immediately executes remote codeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
References a credential file in the home directoryserver.py:731 · References a credential file in the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
CRITICAL
Agent configured for autonomous execution without human approvalserver.py:1296 · Agent configured for autonomous execution without human approvalFix: Declare and request only the permissions the task needs.
AST02
MEDIUM
Remote installer piped to shellserver.py:1707 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
CRITICAL
Agent configured for autonomous execution without human approvalserver.py:406 · Agent configured for autonomous execution without human approvalFix: Declare and request only the permissions the task needs.
AST02
MEDIUM
Remote installer piped to shellserver.py:1408 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shellserver.py:787 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
CRITICAL
Pipe-to-shell patternserver.py:1707 · Pipe-to-shell pattern — downloads and immediately executes remote codeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Access to sensitive file pathsserver.py:876 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsserver.py:1623 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Agent configured for autonomous execution without human approvalserver.py:1420 · Agent configured for autonomous execution without human approvalFix: Declare and request only the permissions the task needs.
AST02
CRITICAL
Pipe-to-shell patternserver.py:1408 · Pipe-to-shell pattern — downloads and immediately executes remote codeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Access to sensitive file pathsserver.py:746 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: 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 configurationserver.py:603 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandserver.py:894 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsserver.py:226 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Agent configured for autonomous execution without human approvalserver.py:713 · Agent configured for autonomous execution without human approvalFix: Declare and request only the permissions the task needs.
AST02
MEDIUM
Process kill commandserver.py:1564 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shellserver.py:1584 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Access to sensitive file pathsserver.py:38 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Pipe-to-shell patternserver.py:550 · Pipe-to-shell pattern — downloads and immediately executes remote codeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Remote installer piped to shellserver.py:550 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
File type combined with upload actionserver.py:1163 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageserver.py:781 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈101 tok
1 file · 6 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

17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Agent configured for autonomous execution without human approval≈ +9 on the totalDeclare and request only the permissions the task needs.
  3. Unclaimed publisher≈ +8 on the totalClaim arcself: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. Does not do what the description says≈ +5 on the totalIn the sandbox the skill never performed the task it claims (no call to the service it is for). Make sure the happy path runs without extra setup, or describe the real behavior.
  5. References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. 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.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim arcselfPropose a patch to the maintainer