ClawHub
Back to skill

Security audit

Supervising Agents

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed supervision checklist for managing subagents and does not contain hidden code, exfiltration, destructive behavior, or unrelated authority.

Install only if you want your agent to actively supervise delegated subagents. Expect it to check task outputs, ask subagents for progress, run relevant verification commands, and report evidence; keep normal caution around any commands the agent chooses to run for a specific task.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% 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 · README.md (reported line 29)May include surrounding context.

Option 1: Copy to Claude Code Skills Directory

bash
mkdir -p ~/.claude/skills/supervising-agents
cp SKILL.md ~/.claude/skills/supervising-agents/

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 29)May include surrounding context.

Option 1: Copy to Claude Code Skills Directory

bash
mkdir -p ~/.claude/skills/supervising-agents
cp SKILL.md ~/.claude/skills/supervising-agents/

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · README.md (reported line 224)May include surrounding context.

md
1. **NEVER wait passively** - actively check
2. **NEVER accept words as proof** - verify files
3. **NEVER let "basically done" slide** - demand specifics
4. **NEVER skip verification** - your reputation is on the line
5. **NEVER report without evidence** - humans trust you

## Time Guidelines

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 426)May include surrounding context.

md
1. **NEVER wait passively** - actively check
2. **NEVER accept words as proof** - verify files
3. **NEVER let "basically done" slide** - demand specifics
4. **NEVER skip verification** - your reputation is on the line
5. **NEVER report without evidence** - humans trust you

## Time Guidelines