ClawHub
Back to skill

Security audit

SN94 Competition Poster

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed helper for drafting SN94 competition proposals and generating a local starter repository, with no evidence of hidden credential access, persistence, exfiltration, or destructive behavior.

Install this if you want help preparing SN94 BitSota competition proposals or starter task repositories. Review any generated repo before publishing, keep secrets and wallet material out of it, and run generated setup or benchmark commands only in an appropriate sandbox.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs the agent to read local reference files and invoke a shell command that writes a new repository skeleton, but it does not declare any permissions for file read, file write, or shell access. That mismatch is a real security issue because consumers and policy engines cannot accurately assess or constrain the skill's capabilities, increasing the chance of unintended command execution or filesystem modification.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill enables implicit invocation while exposing a broad default prompt that can be triggered from natural-language requests without clear scoping or confirmation. In an agent environment, this increases the chance of unintended activation, causing the skill to influence task creation, packaging, or repo generation in contexts the user did not explicitly authorize.

Static analysis

No suspicious patterns detected.