ClawHub
Back to skill

Security audit

gate-info-coinanalysis

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only crypto coin analysis skill; its triggers are somewhat broad, but the artifacts do not show credential use, persistence, or destructive actions.

Use this as an informational crypto research aid, not as financial advice. Be explicit when you want price-only, risk/security, comparison, on-chain, news-only, or technical-only analysis so a more specialized skill is used.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list includes generic phrases like "how is" and "look at," which overlap with common conversational requests and are not narrowly scoped to this skill. Although some routing guidance exists elsewhere, this line's activation description is still broad enough to create accidental matches for unrelated user intents.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Content
## General Rules

⚠️ STOP — You MUST read and strictly follow the shared runtime rules before proceeding.
Do NOT select or call any tool until all rules are read. These rules have the highest priority.
→ Read `./references/gate-runtime-rules.md`
→ Also read `./references/info-news-runtime-rules.md` for gate-info / gate-news shared rules (tool degradation, report standards, security, and output standards).
- **Only call MCP tools explicitly listed in this skill.** Tools not documented here must NOT be called, even if they
Confidence
80% confidence
Finding
Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Static analysis

No suspicious patterns detected.