ClawHub
Back to skill

Security audit

Software Architect

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown architecture-advice guide with no executable code, persistence, credential handling, or hidden high-impact behavior.

Install this if you want structured help making architecture decisions before implementation. Be aware that it may be invoked for broad system-organization questions, so users should still choose a more specific implementation skill when they need code changes rather than design guidance.

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 (2)

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 · SKILL.md (reported line 189)May include surrounding context.

md
- **Don't cargo-cult** — "Netflix does X" doesn't mean you should
- **Don't ignore ops** — A beautiful architecture you can't deploy or monitor is useless
- **Don't skip ADRs** — Future-you will forget why you chose Postgres over MongoDB
- **Don't design without constraints** — Unbounded design is fantasy. Budget, time, and team are real.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description ends with "or any question about how to organize a codebase or system before building," which is broad natural-language trigger guidance rather than a tightly scoped invocation condition. This can overlap with many general coding or planning requests and may cause the skill to activate when a more specific implementation-focused skill would be more appropriate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.