ClawHub
Back to skill

Security audit

engineering-architecture

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only engineering architecture guidance skill with broad but disclosed coding-review instructions and no hidden execution or sensitive access.

Install this if you want an agent to apply architecture and engineering-quality review habits broadly during coding work. Expect it to make the agent more likely to inspect existing patterns, raise security or maintainability concerns, and recommend verification; users who only want narrowly literal edits may find the broad guidance heavier than needed.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation condition is very broad: it says to use this skill whenever making code changes, designing features, or doing code review, which covers a large share of normal development activity. Broad auto-invocation increases the chance the skill injects persistent instructions into unrelated tasks, creating prompt-scope overreach and potentially biasing agent behavior beyond the user's immediate request.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
75% 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 107)May include surrounding context.

md
- inconsistent patterns
- technical debt introduced by the change
- violations of project conventions
Surface meaningful issues even when they are outside the immediate task, but do not expand scope unnecessarily.

## 9. Separate Facts From Preferences
Do not label something as an architectural problem merely because it is different from your preferred style.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

Because this is a JSON manifest-style file, vague trigger rules apply. The prompt text asks broadly for help to refactor code ('Can you help me refactor it?') without any limiting activation conditions, scope constraints, or negative examples, which could overlap with many ordinary software-assistance requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The manifest contains a general request for implementation guidance ('How should I implement this') that is not narrowly scoped to a distinctive trigger or context. Without explicit boundaries or exclusions, the skill could be invoked for common product-development requests rather than a clearly defined architecture-memory use case.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.