ClawHub
Back to skill

Security audit

Harness Engineering

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent repository-documentation and governance helper, with a caution that it can be invoked implicitly and may edit repo docs or CI checks.

Install this if you want Codex to help reorganize repository-local documentation and add lightweight governance checks. Review proposed changes carefully, especially edits to AGENTS.md, docs, package scripts, and CI workflows; disable implicit invocation if you only want the skill to run when explicitly named.

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
91% confidence
Finding

The default prompt is broadly phrased and can be triggered by general requests to 'audit', 'strengthen docs', or 'add checks' without clear boundaries on when the skill should activate. In combination with an agent system that supports heuristic or implicit routing, this can cause the skill to run in contexts the user did not explicitly intend, leading to overbroad repository changes or governance actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Enabling implicit invocation allows the skill to activate without a direct user request, which is risky for a skill designed to make broad structural, documentation, and CI-related changes across a repository. Because this skill's purpose includes modifying governance artifacts and executable checks, unintended activation could materially alter project behavior, workflows, or trust boundaries.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.