ClawHub
Back to skill

Security audit

Subagent Prompt

Security checks for vulnerabilities and agentic risk

Overview

This Markdown skill only helps draft a subagent handoff prompt, and its behavior is disclosed and aligned with that purpose.

Before using it, review the generated handoff prompt for the exact paths, tasks, and verification commands it includes, especially because the follow-on session may run sub-agents to completion. No hidden install, persistence, credential use, or exfiltration behavior was found in the artifact.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

md
- The work fits in one session and one context window — just do it.
- The work is exploratory or experimental and the user explicitly wants to stay in-loop — a heavy orchestration handoff is overkill.
- No concrete artifacts exist to hand off yet — route the user to the [brainstorm-beagle](../../../beagle-analysis/skills/brainstorm-beagle/SKILL.md) or [write-plan](../../../beagle-analysis/skills/write-plan/SKILL.md) skill first to produce the spec and plan that this skill will hand off.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

md
- The work fits in one session and one context window — just do it.
- The work is exploratory or experimental and the user explicitly wants to stay in-loop — a heavy orchestration handoff is overkill.
- No concrete artifacts exist to hand off yet — route the user to the [brainstorm-beagle](../../../beagle-analysis/skills/brainstorm-beagle/SKILL.md) or [write-plan](../../../beagle-analysis/skills/write-plan/SKILL.md) skill first to produce the spec and plan that this skill will hand off.

Static analysis

No suspicious patterns detected.