ClawHub
Back to skill

Security audit

Slv Benchmark

Security checks for vulnerabilities and agentic risk

Overview

This skill appears purpose-aligned for SLV endpoint benchmarking, but users should be aware it may read an existing local ERPC API key file.

Install only if you are comfortable with the agent checking your SLV ERPC API key file for benchmark runs. Avoid sharing generated config or logs if they contain the API key, and prefer redaction or environment-based secret handling when possible.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs reading a local credential file (~/.slv/api.yml) and reusing any ERPC API key found there without requiring explicit user consent or presenting a warning that a secret is being accessed. In an agent context, this creates a credential-handling risk because the agent may access sensitive local secrets and potentially propagate them into generated configs, logs, or downstream command execution.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.