ClawHub
Back to skill

Security audit

Refines ambiguous or high-risk user requests before execution. Trigger when the request is underspecified, likely to benefit from clearer constraints or verification, or when the user explicitly asks to refine, improve, optimize, refactor, or compare approaches. Skip clear single-step instructions and already-well-scoped tasks.

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only prompt-refinement skill that is disclosed, narrowly scoped, and does not request credentials, network access, bundled code execution, or persistent system changes.

This skill appears safe to install for users who want help clarifying ambiguous requests. Be aware that it may sometimes show a rewritten version of your prompt for confirmation, and if paired with a separate session-learning skill it may pass along only abstract preference labels such as whether you chose the refined or original version.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (1)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 117)May include surrounding context.

md
See `references/decision-matrix.md` for the execution-mode decision table.
See `references/non-examples.md` for cases that should usually skip refinement or compare-first.

## Output Rules

### A) Execute Directly

Static analysis

No suspicious patterns detected.