ClawHub
Back to skill

Security audit

AI Forensic Audit (Evidence Chain)

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only forensic audit skill that may handle sensitive evidence but does not install code or perform hidden collection.

Use this skill when you intentionally want an AI provenance or audit-report workflow. Before sharing logs, metadata, internal files, leak evidence, or medical examples, confirm you are authorized to provide them and keep the audit scope narrow.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill exposes a long trigger list including broad terms such as “审计”, “证据链”, and “追踪”-adjacent provenance/audit language that may appear in ordinary enterprise, compliance, or discussion contexts. This can cause unintended invocation of a high-sensitivity forensic/audit workflow, increasing the chance of over-collection requests, privacy-sensitive analysis, or user confusion about when the skill is being activated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The primary display name and main description are in Chinese, while English appears only as a secondary field. This may impose a locale preference without clearly stating that users can choose their language, which can conflict with language-choice policy expectations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.