Security audit

Onchain Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This is a low-impact reference skill that prints static on-chain analysis documentation and shows no evidence of hidden access or persistence.

This appears reasonable to install as a simple reference helper. Users should know its content is generic and its broad description may activate it for general on-chain or blockchain reference requests; do not treat its regulatory or financial text as current professional advice.

A.I.G

Vulnerability Patterns

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
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The description says the skill is a 'Reference tool for devtools' that covers broad topics and offers 'Quick lookup' without specifying how or when it should be invoked. This ambiguity can overlap with many generic documentation or help requests, increasing the risk of unintended activation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.