Back to skill

Security audit

GRC-Agent | SOC 2 Quality Review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed SOC 2 report review aid with no code execution, persistence, credential access, or hidden data movement.

Before installing, users should understand that the skill is for advisory SOC 2 quality review, not legal advice or formal certification. It may process confidential vendor assurance reports, so users should provide only documents they are authorized to review and handle any generated follow-up requests through normal GRC/procurement channels.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
- Risk posture: Conservative / Balanced / Lenient
- Evidence strictness: Escalate on Unknown / Conditional with deadline / Case-by-case

## Output rules

### 1) Escalate on Unknown
- Conservative: any critical unknown (S7/S8/S12/S15/S16/S25) => Escalate
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Static analysis

No suspicious patterns detected.