ClawHub
Back to skill

Security audit

Brainstorm

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent brainstorming skill with no code, persistence, or hidden privilege use; its main caution is that domain checks may involve external lookups.

This skill is reasonable to install for creative ideation. Be aware that it may activate on broad exploratory phrasing, and ask the agent not to check domain availability unless you are comfortable sending candidate names to external lookup services.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 116)May include surrounding context.

md
## Anti-Patterns

- **Don't judge during generation** — Validation comes later
- **Don't anchor on the first idea** — First idea is rarely the best
- **Don't brainstorm alone** — Ask the user to react, build, and remix
- **Don't be generic** — "Build an app" is not an idea. "A WhatsApp bot that reminds freelancers to invoice overdue clients" is.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list is broad enough to match common conversational phrases such as 'help me explore,' 'what if,' or 'options,' which can lead to accidental invocation outside the intended context. Unintended routing can override more appropriate skills or system behavior, causing the agent to enter brainstorming mode when the user did not actually request open-ended ideation.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill goes beyond ideation by instructing the agent to check domain availability, which is an external validation/enrichment action rather than pure brainstorming. This can cause scope creep, unexpected tool or network use, and may trigger side effects or privacy leakage if the agent queries third-party services during what should be a low-risk creative session.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.