ClawHub
Back to skill

Security audit

Usable Stability Loop · The 99/80 Loop

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown delivery-guidance skill that tells agents to prioritize usable, stable MVP-style work and shows no hidden execution, data access, or persistence behavior.

Install this if you want an agent to favor usable, stable, low-overhead delivery for MVP-like work. Avoid making it the dominant rule for security-sensitive, compliance-bound, or high-risk engineering tasks unless you also provide stricter validation and quality requirements.

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
92% confidence
Finding

The manifest description is broadly phrased around common goals like fast development, efficient deployment, continuous evolution, and avoiding over-engineering, which can cause the skill to activate in many ordinary software-assistance contexts beyond its narrowly intended use. Overbroad activation increases the chance that this delivery philosophy will override more task-specific guidance, leading agents to prematurely de-scope work such as hardening, validation, or domain-specific safeguards.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file contains substantial end-user-facing content in both Chinese and English, but it does not state whether the skill supports multiple languages by design or whether users can choose their preferred language. Under the language/locale policy rule, forcing or assuming a language without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.