Back to skill

Security audit

Difficult Conversation Rehearser

Security checks for vulnerabilities and agentic risk

Overview

This skill only generates hard-conversation rehearsal text and does not show hidden access, persistence, data exfiltration, or unsafe system changes.

Install only for drafting and rehearsing difficult conversations. Do not rely on it for emergencies, ongoing abuse, threats, coercion, legal strategy, or safety planning; use appropriate local emergency, crisis, legal, or specialist support for those situations.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly detects inputs mentioning abuse, threats, violence, or coercion, but only adds a brief inline note in the generated output rather than enforcing a clear safety escalation path or providing strong upfront disclosure. In a safety-critical context, users may rely on the rehearsal guidance instead of being redirected to crisis, legal, shelter, or emergency resources, which can delay protective action.

Content

No source excerpt is available for this finding.