Back to skill

Security audit

Clash of Coins - Agentic Gateway

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for Clash of Coins discovery and checkout, but its network helper is too broadly scoped and could probe non-public services or disclose recipient identifiers to arbitrary origins.

Install only if you trust the target Clash of Coins gateway and can keep the agent restricted to known public HTTPS origins. Do not run the discovery helper against internal, local, or untrusted URLs, and treat nickname/address recipient probes and buy/fund steps as sensitive actions that should require explicit user approval.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/discover-gateway.mjs:75
Finding

Arbitrary-Origin SSRF and Internal Service Reconnaissance

Content
View full analysis
controller.abort(), timeoutMs); try { const response = await fetch(url, { method: 'GET', redirect: 'follow', signal: controller.signal, }); const text = await response.text(); return { path, url, status: response.status, ok: response.ok, durationMs: Date.now() - startedAt, contentType: response.headers.get('content-type'), body: text, }; ``` The arbitrary origin is subsequently used to probe a fixed collection of paths: ```js const paths = [ '/', '/health', '/openapi.json', '/openapi.full.json', '/mcp.json', '/skills/index.json', '/catalog', '/.well-known/agent.json', '/.well-known/agents.json', '/.well-known/x402', '/.well-known/mpp', '/llms.txt', '/skill.md', '/shop', '/shop/health', '/shop/openapi.json', '/shop/openapi.full.json', '/shop/llms.txt', '/shop/skill.md', '/shop/api/shop/items', '/shop/.well-known/agent.json', '/shop/.well-known/agents.json', '/shop/.well-known/x402', '/shop/.well-known/mpp', ]; ``` ### Technical Analysis The `--origin` validation only verifies that the parsed URL ...[truncated 2889 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (17)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 4)May include surrounding context.

md
compatibility: Requires Node.js 18+ to run scripts/discover-gateway.mjs and outbound HTTPS access to the target gateway origin. Works in Agent Skills-compatible

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

md
compatibility: Requires Node.js 18+ to run scripts/discover-gateway.mjs and outbound HTTPS access to the target gateway origin. Works in Agent Skills-compatible

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill explicitly requires outbound HTTPS access and instructs the agent to run a Node.js discovery script, but it does not declare any tool scope such as permissions or allowed-tools. That creates a capability mismatch where an agent may execute networked actions without clear least-privilege boundaries, increasing the risk of unintended requests to attacker-controlled origins or unsafe transaction flows.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
80% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · evals/trigger-queries.json (reported line 67)May include surrounding context.

json
"should_trigger": false
  },
  {
    "query": "Create a cron job that pings /health every minute and posts alerts to Slack.",
    "should_trigger": false
  },
  {

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 11)May include surrounding context.

md
For live deployments:

- unified gateway skill: `/skill.md`
- published reusable skill: `/skills/clashofcoins-universal/SKILL.md`
- compatibility aliases: `/skills/SKILL.md`, `/skills/clashofcoins-universal/skill.md`, `/skills/clashofcoins-universal`, `/skills/clashofcoins/SKILL.md`, `/skills/clashofcoins/skill.md`, `/skills/clashofcoins`
- published skills index: `/skills/index.json`
- well-known skills index alias: `/.well-known/skills/index.json`

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/client-installation.md (reported line 10)May include surrounding context.

md
For live deployments:

- unified gateway skill: `/skill.md`
- published reusable skill: `/skills/clashofcoins-universal/SKILL.md`
- compatibility aliases: `/skills/SKILL.md`, `/skills/clashofcoins-universal/skill.md`, `/skills/clashofcoins-universal`, `/skills/clashofcoins/SKILL.md`, `/skills/clashofcoins/skill.md`, `/skills/clashofcoins`
- published skills index: `/skills/index.json`
- well-known skills index alias: `/.well-known/skills/index.json`

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/client-installation.md (reported line 19)May include surrounding context.

md
For live deployments:

- unified gateway skill: `/skill.md`
- published reusable skill: `/skills/clashofcoins-universal/SKILL.md`
- compatibility aliases: `/skills/SKILL.md`, `/skills/clashofcoins-universal/skill.md`, `/skills/clashofcoins-universal`, `/skills/clashofcoins/SKILL.md`, `/skills/clashofcoins/skill.md`, `/skills/clashofcoins`
- published skills index: `/skills/index.json`
- well-known skills index alias: `/.well-known/skills/index.json`

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/client-installation.md (reported line 31)May include surrounding context.

md
For live deployments:

- unified gateway skill: `/skill.md`
- published reusable skill: `/skills/clashofcoins-universal/SKILL.md`
- compatibility aliases: `/skills/SKILL.md`, `/skills/clashofcoins-universal/skill.md`, `/skills/clashofcoins-universal`, `/skills/clashofcoins/SKILL.md`, `/skills/clashofcoins/skill.md`, `/skills/clashofcoins`
- published skills index: `/skills/index.json`
- well-known skills index alias: `/.well-known/skills/index.json`

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/client-installation.md (reported line 32)May include surrounding context.

md
For live deployments:

- unified gateway skill: `/skill.md`
- published reusable skill: `/skills/clashofcoins-universal/SKILL.md`
- compatibility aliases: `/skills/SKILL.md`, `/skills/clashofcoins-universal/skill.md`, `/skills/clashofcoins-universal`, `/skills/clashofcoins/SKILL.md`, `/skills/clashofcoins/skill.md`, `/skills/clashofcoins`
- published skills index: `/skills/index.json`
- well-known skills index alias: `/.well-known/skills/index.json`

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/client-installation.md (reported line 37)May include surrounding context.

md
For live deployments:

- unified gateway skill: `/skill.md`
- published reusable skill: `/skills/clashofcoins-universal/SKILL.md`
- compatibility aliases: `/skills/SKILL.md`, `/skills/clashofcoins-universal/skill.md`, `/skills/clashofcoins-universal`, `/skills/clashofcoins/SKILL.md`, `/skills/clashofcoins/skill.md`, `/skills/clashofcoins`
- published skills index: `/skills/index.json`
- well-known skills index alias: `/.well-known/skills/index.json`

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
- unified gateway skill: `/skill.md`
- published reusable skill: `/skills/clashofcoins-universal/SKILL.md`
- compatibility aliases: `/skills/SKILL.md`, `/skills/clashofcoins-universal/skill.md`, `/skills/clashofcoins-universal`, `/skills/clashofcoins/SKILL.md`, `/skills/clashofcoins/skill.md`, `/skills/clashofcoins`
- published skills index: `/skills/index.json`
- well-known skills index alias: `/.well-known/skills/index.json`

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/client-installation.md (reported line 11)May include surrounding context.

md
- unified gateway skill: `/skill.md`
- published reusable skill: `/skills/clashofcoins-universal/SKILL.md`
- compatibility aliases: `/skills/SKILL.md`, `/skills/clashofcoins-universal/skill.md`, `/skills/clashofcoins-universal`, `/skills/clashofcoins/SKILL.md`, `/skills/clashofcoins/skill.md`, `/skills/clashofcoins`
- published skills index: `/skills/index.json`
- well-known skills index alias: `/.well-known/skills/index.json`

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
- unified gateway skill: `/skill.md`
- published reusable skill: `/skills/clashofcoins-universal/SKILL.md`
- compatibility aliases: `/skills/SKILL.md`, `/skills/clashofcoins-universal/skill.md`, `/skills/clashofcoins-universal`, `/skills/clashofcoins/SKILL.md`, `/skills/clashofcoins/skill.md`, `/skills/clashofcoins`
- published skills index: `/skills/index.json`
- well-known skills index alias: `/.well-known/skills/index.json`

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/client-installation.md (reported line 11)May include surrounding context.

md
- unified gateway skill: `/skill.md`
- published reusable skill: `/skills/clashofcoins-universal/SKILL.md`
- compatibility aliases: `/skills/SKILL.md`, `/skills/clashofcoins-universal/skill.md`, `/skills/clashofcoins-universal`, `/skills/clashofcoins/SKILL.md`, `/skills/clashofcoins/skill.md`, `/skills/clashofcoins`
- published skills index: `/skills/index.json`
- well-known skills index alias: `/.well-known/skills/index.json`

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
- unified gateway skill: `/skill.md`
- published reusable skill: `/skills/clashofcoins-universal/SKILL.md`
- compatibility aliases: `/skills/SKILL.md`, `/skills/clashofcoins-universal/skill.md`, `/skills/clashofcoins-universal`, `/skills/clashofcoins/SKILL.md`, `/skills/clashofcoins/skill.md`, `/skills/clashofcoins`
- published skills index: `/skills/index.json`
- well-known skills index alias: `/.well-known/skills/index.json`

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/client-installation.md (reported line 11)May include surrounding context.

md
- unified gateway skill: `/skill.md`
- published reusable skill: `/skills/clashofcoins-universal/SKILL.md`
- compatibility aliases: `/skills/SKILL.md`, `/skills/clashofcoins-universal/skill.md`, `/skills/clashofcoins-universal`, `/skills/clashofcoins/SKILL.md`, `/skills/clashofcoins/skill.md`, `/skills/clashofcoins`
- published skills index: `/skills/index.json`
- well-known skills index alias: `/.well-known/skills/index.json`

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script appends user-supplied --nickname or --address values to /shop/api/shop/items query parameters and then sends them to an arbitrary target origin. That transmits potentially sensitive recipient identifiers to the remote gateway during discovery, and the help/output do not clearly warn the operator that this data will be disclosed to the target service and may be logged in URLs, proxies, browser/server logs, or monitoring systems.

Content

No source excerpt is available for this finding.