ClawHub
Back to skill

Security audit

creem-audit-kit

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill generates Creem compliance policy templates; the scanner hits are legal/compliance wording rather than instructions to control the agent.

Install only if you want help drafting Creem-focused compliance pages. Treat the output as a draft: replace all TODOs/placeholders, choose one refund policy, remove unused template text, and have the final legal language reviewed for your product and jurisdiction before publishing.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Instruction Override

High
Category
Prompt Injection
Confidence
90% confidence
Finding

This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Content

Scanner excerpt · assets/legal-pages/terms-of-service.md (reported line 28)May include surrounding context.

md
You agree not to misuse the Service, including by:
- violating laws or regulations
- infringing intellectual property or privacy rights
- attempting to bypass security controls
- distributing malware, spam, or engaging in fraud
- generating or distributing prohibited content (see Content Policy)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · references/creem-preflight-checklist.md (reported line 29)May include surrounding context.

md
- [ ] Pricing page shows what the customer receives (limits/credits/seats)
- [ ] Pricing shows billing period (monthly/annual) and currency
- [ ] If credits are used: explain what a credit is and when it is consumed
- [ ] No misleading “unlimited” claims without constraints/abuse guardrails

## 5) Checkout flow disclosures
- [ ] Before payment, user can access Terms/Privacy/Refund links

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
90% confidence
Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · references/creem-preflight-checklist.md (reported line 39)May include surrounding context.

md
## 6) Content policy covers prohibited use
- [ ] Prohibits illegal content, harassment/hate, explicit sexual content involving minors
- [ ] Prohibits IP infringement, impersonation, fraud
- [ ] Prohibits attempts to bypass safety/security controls
- [ ] Explains enforcement (suspension/termination, reporting channel)

## 7) Privacy policy covers the basics

Instruction Override

High
Category
Prompt Injection
Confidence
90% confidence
Finding

This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Content

Scanner excerpt · references/creem-preflight-checklist.md (reported line 39)May include surrounding context.

md
## 6) Content policy covers prohibited use
- [ ] Prohibits illegal content, harassment/hate, explicit sexual content involving minors
- [ ] Prohibits IP infringement, impersonation, fraud
- [ ] Prohibits attempts to bypass safety/security controls
- [ ] Explains enforcement (suspension/termination, reporting channel)

## 7) Privacy policy covers the basics

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The policy states that the service collects generated outputs metadata and performance logs, but it does not clearly warn users what those categories include, why they are necessary, whether they may contain personal or sensitive data, or how they affect user privacy. This creates transparency and compliance risk because users may not reasonably understand the scope of monitoring and logging, especially in a product that processes user-generated content.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The description says to use the skill when 'preparing for Creem review or getting unblocked after rejection,' but it does not define specific trigger phrases, boundaries, or exclusions for when this skill should be selected versus other legal/compliance drafting skills. This makes activation somewhat ambiguous for any request about website policies or compliance packs, increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file includes unresolved template placeholders and multiple alternative policy blocks that instruct the operator to 'choose one and delete the rest.' If published or consumed as-is, the refund policy can become ambiguous, contradictory, or incomplete, which creates legal/compliance risk and may let an attacker or careless deployer present misleading terms to users.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.