ClawHub
Back to skill

Security audit

Community Growth Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a community-management playbook with no executable code, hidden persistence, or secret data handling, though users should apply privacy and moderation controls when using it.

Installers should treat this as advisory community-operations content. Before letting an agent send DMs, tag members, change roles, delete posts, mute, ban, or email members, require explicit operator approval and make sure members have clear privacy notice, consent or opt-out options, and platform-policy compliance.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The onboarding and re-engagement guidance recommends direct messages, tagging users based on inferred interests, and tracking behavioral milestones without a clear user-facing privacy notice or consent mechanism. This creates privacy and compliance risk because an implementing agent or operator could monitor engagement and initiate outreach in ways users did not expect, especially under GDPR/CCPA or platform policy constraints.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 301)May include surrounding context.

md
4. **Give more than you take.** Answer questions. Share resources. Celebrate others.
5. **Keep it on-topic.** #off-topic exists for a reason.
6. **No hate speech, harassment, or discrimination.** Zero tolerance. One strike.
7. **Protect privacy.** Don't share others' information without consent.

## Enforcement
- **Gentle reminder** → **Warning** → **24h mute** → **Permanent ban**

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill exposes very broad natural-language commands such as "Design my community," "Handle [situation]," and "Quarterly review" that can easily match ordinary user requests outside a narrowly scoped community-planning context. In agent environments, overly generic triggers increase the chance of unintended activation, prompt overlap with other skills, and execution in contexts where the user did not explicitly intend to invoke this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The Quick Start section lists activation examples like "Design my community" and "Build growth strategy" without clarifying whether these are exact triggers, examples, or constrained to a specific context. These phrases are broad enough to overlap with normal conversation, which could cause unintended invocation if the runtime uses natural-language matching.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 344)May include surrounding context.

md
- Rotate on-call moderators (never one person 24/7)
- Maximum 2-hour active moderation shifts
- Monthly moderator check-in: "How are you doing?"
- Clear escalation path — mods shouldn't handle everything alone
- Celebrate moderator contributions publicly

---

Static analysis

No suspicious patterns detected.