Back to skill

Security audit

Ciderbox

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Ciderbox/Orchard usage guide, with user-directed VM and secret-handling commands that deserve caution but are aligned with its stated purpose.

Install only if you intend to let agents manage local Apple container VMs. Treat 'chop' commands as destructive to running Ciderbox environments, and avoid 'secrets push --all' unless every running tree and workload is trusted; prefer short-lived, least-privilege credentials and rotate them after use.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Chaining Abuse

High
Category
Tool Misuse
Confidence
75% confidence
Finding

Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.

Content

Scanner excerpt · SKILL.md (reported line 148)May include surrounding context.

sh
gofmt -w internal/cli/*.go
go test ./...
cd /tmp && rm -rf ciderbox-init-smoke && mkdir ciderbox-init-smoke
cd /tmp/ciderbox-init-smoke && git init -q && ciderbox init

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

This markdown file includes cleanup commands like ciderbox chop and later ciderbox orchard chop --yes, which imply destructive teardown of running VMs, but the skill description does not explicitly warn users that these commands will irreversibly terminate environments. Under the markdown-specific warning rule, behaviors affecting system state should be disclosed clearly.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The secrets workflow instructs users to push credentials into running trees without any warning about trust boundaries, secret lifetime, or the risk of distributing credentials to multiple agent-controlled VMs. In the orchard context, those trees execute tasks and may process untrusted repositories or prompts, so broad secret propagation increases the chance of credential exposure or misuse.

Content

No source excerpt is available for this finding.