ClawHub
Back to skill

Security audit

Abi Toolchain

Security checks across malware telemetry and agentic risk

Overview

The skill is legitimate ABI tooling, but its sync script can write outside the intended folder and has a fallback command-safety issue.

Review or patch scripts/sync-abi.sh before using it in CI or automatic build hooks. Only run it in trusted repositories, validate .abi-sync entries, ensure output paths stay under ABI_DEST, and prefer a version that passes file paths to Python as arguments rather than interpolating them into code.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger list is very broad and includes generic terms like 'ABI', 'deployment artifacts', and 'any question about syncing frontend code to contract changes', which can cause the skill to activate in situations only loosely related to its intended scope. Over-broad invocation increases the chance of inappropriate routing, irrelevant guidance, or context hijacking by pulling this skill into unrelated smart-contract conversations.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.