ClawHub
Back to skill

Security audit

RSAD Copilot

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only IBM RSAD/FTM design helper with one broad trigger phrase, but no hidden execution, persistence, credential handling, or exfiltration behavior.

Install this if you want RSAD/FTM design guidance. Keep its use limited to RSAD, UML, FSM, FTM interface design, and related SQL export planning, and require normal human review before applying generated SQL to DB2 or opening version-control PRs.

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 (1)

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The phrase 'When in doubt, trigger this skill' creates an overly broad activation condition that can cause the skill to be invoked outside its intended RSAD/FTM design scope. Over-triggering increases the chance that unrelated user prompts are routed into a highly specialized workflow, which can cause incorrect guidance, accidental disclosure of irrelevant internal process details, or interference with safer/more appropriate skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.