Aha Claudecode Omc

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 9:37 AM UTC
• Version: 1.1.0

Overview

This skill is a disclosed orchestration guide for Claude Code with OMC, with some install-version caution but no hidden persistence or malicious behavior found.

Before installing or upgrading, verify the OMC plugin and aha-orch source, prefer pinned commits or versions over latest commands, and avoid using delegated agents for secrets, browser/session material, credentials, live account actions, or destructive work unless you explicitly approve the scope.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

• Location: SKILL.md:67

Finding

Unpinned Remote Installation and Upgrade Dependencies

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, lines 67–75
Vulnerability Type: T08: Insecure Dependencies
Risk Level: Medium

Vulnerable Code

markdown

- [OMC repository](https://github.com/Yeachan-Heo/oh-my-claudecode)
- OMC install command: `claude plugin marketplace add Yeachan-Heo/oh-my-claudecode` (verify against official repo before use)
- [Claude Code subagents documentation](https://docs.anthropic.com/en/docs/claude-code/sub-agents)
- Read `./references/capability-orchestration.md` before applying orchestration logic. It is the source of truth for orchestration steps, transparency, re-orchestration, out-of-session, cost awareness, and the 7-field discovery schema.

## Source & Upgrade

- **Repository**: https://github.com/its-How/aha-orch
- **Note**: This skill is part of the aha-orch multi-skill repository (contains aha-orch-xx, aha-codex-omx, aha-opencode-omo, aha-claudecode-omc).
- **Upgrade**: Run `git pull` in the aha-orch repo, or re-run `npx skills add its-how/aha-orch` to get the latest version.

Technical Analysis

The documented installation and upgrade procedures resolve mutable third-party content without pinning an immutable package version, repository tag, commit hash, or content digest.

In particular, npx skills add its-how/aha-orch may download and execute the currently published skills CLI before retrieving the current repository content. The plugin marketplace command and git pull similarly trust the latest upstream state. Consequently, the effective code installed by these commands can change after this Skill has been reviewed.

The recommendation to verify OMC against its official repository helps prevent accidental use of an unrelated source, but it does not provide cryptographic integrity, reproducibility, or protection against compromise of the legitimate publisher account, package, marketplace entry, or repository.

Attack Path

1. An attacker compromises an upstream npm publisher ...[truncated 1678 chars]

Remediation

View remediation

Remediation Suggestions

1. Pin the skills CLI to a reviewed, exact version instead of invoking an implicitly current release through npx.
2. Pin the Skill repository and OMC plugin to immutable release tags or, preferably, reviewed commit hashes.
3. Publish and verify cryptographic checksums or signatures for downloaded artifacts before installation.
4. Replace generic git pull guidance with a reproducible upgrade procedure that fetches a specific reviewed revision.
5. Require users to inspect the upstream diff between the currently installed revision and the proposed revision before upgrading.
6. Avoid running installation commands with administrative privileges and document the minimum required permission scope.
7. Where supported, use lockfiles, package-manager integrity metadata, trusted registries, and signature verification.
8. Document an explicit rollback procedure to restore the previously reviewed commit or package version if validation fails.

SkillSpector

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Rogue Agent: Self-Modification, Session Persistence
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

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 · SKILL.md (reported line 17)May include surrounding context.

md

Agent-facing, brain-led capability orchestration for [Claude Code](https://docs.anthropic.com/en/docs/claude-code/overview) with [oh-my-claudecode (OMC)](https://github.com/Yeachan-Heo/oh-my-claudecode) installed. This skill enables the agent to discover, select, combine, and reselect available capability surfaces (native runtime, enhancement layer, skill, MCP, command, subagent, worktree) to build the lowest-sufficient task-lifecycle capability route for the task.

For non-trivial work, keep the current Claude Code session as the decision maker and final integrator: own goal, constraints, decomposition, permission checks, integration, acceptance, verification, and final answer. Resolve available agents at runtime and prefer bounded lanes for separable units when they improve evidence; do not delegate merely to create fan-out.

OMC provides a rich agent surface: 32+ specialized agents, Team Mode, Autopilot, Ultrawork, Ralph, and Pipeline orchestration. This skill activates per-task agent matching — the agent selects the OMC capability surface that best fits the task unit rather than defaulting to a fixed agent.

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 · SKILL.md (reported line 62)May include surrounding context.

md

## Rollback / Deactivation

- **Soft**: Stop invoking OMC-specific capabilities and re-orchestrate to native Claude Code capability route. No persistent state is maintained by this skill.
- **Hard**: Remove the skill directory from your skills path (e.g., `~/.claude/skills/aha-claudecode-omc/`).
- **Partial**: If only a specific OMC feature is unavailable, deactivate that feature only and keep using available OMC agent surfaces.

## Reference

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 70% confidence

Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.