Back to skill

Security audit

Transactional Game Analysis

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only conversation-analysis skill with no code execution, network access, persistence, or credential handling; its main caveat is that it can be implicitly invoked on sensitive conversations.

Install only if you are comfortable with the agent applying this framework to pasted or active two-person conversations. Avoid sending highly sensitive transcripts unless you intend them to be analyzed, and treat the output as interpretive guidance rather than diagnosis or professional mental-health advice.

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
  • 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
93% confidence
Finding

The skill enables implicit invocation while advertising a broad, generic capability to analyze two-person conversations. That makes it easier for the platform to auto-trigger the skill in contexts the user may not explicitly intend, potentially exposing sensitive conversation content to the skill or causing unrequested behavioral steering. The conversational-analysis context increases risk because many ordinary prompts could match this description, so trigger ambiguity is meaningful rather than theoretical.

Content

No source excerpt is available for this finding.