ClawHub
Back to skill

Security audit

decision-log

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple decision-log template that stores decision notes and event metadata, with no bundled executable code or hidden behavior found.

Install only if you want decision records saved under memory/decisions and event metadata written under events. Use explicit prompts when recording decisions, and avoid logging sensitive personal, business, or security decisions unless that persistence is acceptable.

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)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The feature description mentions recording decisions but does not warn users that the skill will automatically create files and publish an event, which can expose sensitive operational or personal information without informed consent. The risk is heightened by the 30-day auto-review and event bus integration, since data is not only stored but also propagated to other components.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger phrases are broad enough to match ordinary discussion about past choices, which can cause the skill to activate unexpectedly and persist potentially sensitive content. In this skill, unintended activation is more dangerous because activation leads to file creation and downstream event publication, creating side effects beyond a simple response.

Static analysis

No suspicious patterns detected.