ClawHub
Back to skill

Security audit

Delivery Checklist

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only delivery checklist that shapes review output but does not request dangerous access or hidden behavior.

Install this if you want a structured delivery-review checklist. Be aware it may make the agent answer in a longer fixed format during matching review workflows, so users who prefer flexible formatting may want to edit or narrow the trigger text.

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 (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
70% confidence
Finding

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
**Plan → Implement (Red→Green→Refactor) → Produce Artifacts → PR → Verify CI → Deliver**

Always respond in this order:
1. **Plan** (checklist)
2. **Actions & Artifacts** (logs, screenshots, test output)
3. **Findings**

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The description says to use the skill when 'Final PR review before merge' or 'Verifying completeness of implementation,' which are broad situations that can apply to many routine workflows. It does not define specific trigger phrases, boundaries, or exclusion conditions, increasing the chance of accidental or overly frequent invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The instruction 'Always respond in this order' imposes a mandatory output structure regardless of user preference. While not a language restriction, it is a natural-language policy constraint that overrides user choice in how responses are formatted.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.