ClawHub
Back to skill

Security audit

Dpia Drafter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent GDPR DPIA drafting aid that asks for relevant privacy inputs and produces a draft for human DPO/controller review without hidden execution or persistence.

Before installing, users should be aware that the skill is designed to collect confidential privacy and architecture information needed for a DPIA. Use category-level descriptions instead of raw personal records, and keep DPO/controller review because the skill only drafts the assessment and does not provide final legal sign-off.

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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · SKILL.md (reported line 188)May include surrounding context.

md
| Illegitimate access | Breach, malicious insider, mis-shared link |
| Unwanted modification | Tampering, model drift on protected attributes |
| Data loss / unavailability | Ransomware, deletion, no backup |
| Unlawful disclosure | Cross-border transfer without safeguards, public exposure |
| Loss of control | Unbounded retention, no real consent, no erasure path |
| Discrimination / unfair treatment | Profiling bias, scoring on sensitive attributes |
| Re-identification | De-anonymised dataset, linkage with external sources |

Static analysis

No suspicious patterns detected.