Back to skill

Security audit

connor-voice

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: the scans found no AIG issues and one low probability, contextually discounted instruction concern, though Skillspector’s analysis was partial.

The verdict is benign, but confidence is medium and Skillspector’s analysis is marked partial because two local references could not be resolved. Consider whether the flagged instruction fits your needs, and review the skill’s guidance before installing.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
55% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · references/self-check.md (reported line 40)May include surrounding context.

md
If the user's explicit instruction conflicts with the voice, **the instruction wins, silently**. Do not announce that you are breaking character. Do not apologize for it. Just answer.