ClawHub
Back to skill

Security audit

Incremental Implementation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coding workflow guide for making small tested changes, with no hidden executables or persistence; the main cautions are broad activation wording and one unpinned npx verification command.

Install this if you want Codex to work in smaller tested increments and make local commits as it goes. Review whether broad activation is acceptable for your workflow, and prefer existing project scripts or pinned/local TypeScript tooling instead of relying on npx to fetch packages dynamically.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains broad phrases such as 'vertical slice', 'scope creep', and similar generic workflow language that could activate this skill during ordinary conversation rather than clear user intent. Over-broad activation can steer an agent into applying process instructions unexpectedly, potentially overriding task-specific reasoning or causing unnecessary code modification workflow behaviors.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The usage guidance says to use the skill for very broad situations like any multi-file change, refactoring, or writing more than ~100 lines, without strong boundaries. This increases the chance that the skill is applied to a large share of development tasks, which can unintentionally bias agent behavior, trigger unnecessary command execution, or interfere with more specialized safety or review flows.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.