ClawHub
Back to skill

Security audit

Coding Contract

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation helper that creates coding specification files and does not show hidden execution, exfiltration, or privilege-seeking behavior.

Install this if you want an agent to read relevant project context and create reusable Markdown coding specs. Specify the desired output path, or ask for the spec in chat first, if you do not want a new docs/specs file created automatically.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list ends with a broad semantic clause ('or when a brainstorming design document needs to be converted into an actionable engineering plan'), which can cause the skill to activate for loosely related requests beyond the explicit phrases. Over-broad activation increases the chance the agent applies this skill in the wrong context, leading to unintended file generation or workspace changes without the user clearly requesting this specific behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to output a file named spec.md, choose a default path, and 'Save the file' without requiring explicit user confirmation or warning that the workspace will be modified. This can result in unauthorized or surprising file writes, which is risky in agent environments because an unintended trigger or ambiguous request could mutate the repository state.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.