ClawHub
Back to skill

Security audit

functional-test-case-standard

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown test-case writing and review guide with no hidden execution or privileged behavior found.

Installers should treat this as a test-case methodology skill. Be mindful that generated requirement documents may contain private business details, so avoid online XMind converters unless you explicitly approve sharing that content with a third party.

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 (4)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
- Test: confirm action, cancel action, timeout without action

**Generated Verification Items**:
- [ ] Verify export with exactly 10,000 records: no warning displayed, export proceeds
- [ ] Verify export with 9,999 records: no warning displayed, export proceeds
- [ ] Verify export with 10,001 records: warning message "This report contains 10,001 records. Export may take several minutes. Continue?" is displayed
- [ ] Verify clicking 'Confirm' on warning: export proceeds
Confidence
80% 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.

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
- Test: confirm action, cancel action, timeout without action

**Generated Verification Items**:
- [ ] Verify export with exactly 10,000 records: no warning displayed, export proceeds
- [ ] Verify export with 9,999 records: no warning displayed, export proceeds
- [ ] Verify export with 10,001 records: warning message "This report contains 10,001 records. Export may take several minutes. Continue?" is displayed
- [ ] Verify clicking 'Confirm' on warning: export proceeds
Confidence
80% 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.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill description is broad enough to match many generic testing- or review-related user requests, which can cause the agent to invoke this skill in contexts the user did not explicitly intend. Over-broad auto-invocation can misroute tasks, expose unrelated user content to the skill’s processing logic, and increase the chance of prompt-scope confusion or unintended behavior.

Natural-Language Policy Violations

Low
Confidence
93% confidence
Finding
Line L513 includes the instruction "Do not use checked checkbox `[x]`,统一 use `[ ]`", which embeds a Chinese-only term in an otherwise English document and effectively enforces a specific language/locale convention without offering user choice. This is a natural-language policy concern because the document does not state that it is region-specific or provide an opt-in for mixed-language output.

Static analysis

No suspicious patterns detected.