oh-my-opencode@5.1.4
The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools
AI Security Review
scanned 1mo ago · by lpm-firewall-aiSource establishes explicit-user-command agent configuration mutation with broad default permissions and suppressed warnings. This warrants a capability warning under the supplied policy, without evidence sufficient to classify the package as malicious.
Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review
Trigger
Running install/setup with Codex selected and autonomous permissions enabled, which is the default.
Impact
Later agent sessions inherit reduced execution restrictions and persisted plugin trust; automatic remote updates were not established by the inspected code.
Mechanism
The installer rewrites Codex config.toml to disable approvals, permit full access, hide warnings, and enable trusted package hooks.
AI rationale
Source establishes explicit-user-command agent configuration mutation with broad default permissions and suppressed warnings. This warrants a capability warning under the supplied policy, without evidence sufficient to classify the package as malicious.
Evidence
dist/cli/index.jsdist/cli-node/index.jsconfig.toml
Decision evidence
public snapshotAI called this Suspicious at 94.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The explicit install/setup CLI invokes the Codex installer with the selected autonomous-permissions setting.
- Codex autonomous permissions default to enabled unless explicitly overridden.
- Autonomous setup sets approval_policy to never, selects danger-full-access, and removes the network_access setting.
- The Node bundle also removes the Windows sandbox setting and hides full-access and world-writable warnings.
- The installer updates Codex config.toml, saves trusted plugin hooks, and writes agent configuration.
- The npm postinstall cache deletion is limited to directories matching this package's plugin-name prefixes.
Evidence against
- The configuration changes occur through explicit CLI setup, rather than the inspected npm postinstall hook.
- Users can disable autonomous permission changes with --no-codex-autonomous.
- The flagged QA locations contain rejection-test inputs; the flagged bundle locations copy package-owned MCP runtimes.
Behavioral surface
ChildProcessCryptoDynamicRequire
Source & flagged code
23 flaggedpackage.jsonView file
1Install-time code directly mutates a foreign AI-agent control surface:
L62: "docs/reference/web-terminal-visual-qa.md",
L63: ".opencode/command",
L64: ".opencode/skills",
L65: ".agents/command",
L66: ".agents/skills",
L67: "packages/lsp-tools-mcp/package.json",
...
L97: "packages/prompts-core/prompts/ultrawork/codex.md",
L98: "packages/omo-codex/plugin/.codex-plugin",
L99: "!packages/omo-codex/plugin/node_modules",
...
L147: "test:fast": "bun run script/test-fast.ts",
L148: "test:senpi": "bun run build:senpi-plugin && tsgo --noEmit -p packages/omo-senpi/tsconfig.json && bun test --timeout 20000 packages/omo-senpi && bun test ./.agents/skills/senpi-qa/...
L149: "test:windows-codex": "bun run test:codex",
Write operation from dist/tui.js:
L2183: // packages/utils/src/xdg-data-dir.ts
L2184: i
Critical
Ai Agent Control Hijack
Source creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.
package.jsonView on unpkg · L1•scripts.postinstall = node postinstall.mjs
High
Install Time Lifecycle Scripts
Package defines install-time lifecycle scripts.
package.jsonView on unpkg•scripts.postinstall = node postinstall.mjs
Findings
4 Critical14 High9 Medium6 Low
CriticalSame File Env Network Executiondist/skills/browser/runtime/omowright/index.js
CriticalDownload Executedist/skills/browser/runtime/omowright/index.js
CriticalRemote Response Code Executiondist/index.js
CriticalAi Agent Control Hijackpackage.json
HighInstall Time Lifecycle Scriptspackage.json
HighChild Processbin/oh-my-opencode.js
HighShelldist/cli-node/index.js
HighEvaldist/skills/ulw-research/scripts/layout-probe.test.ts
HighCredential Redirect Persistencedist/index.js
HighCommand Output Exfiltrationdist/cli-node/index.js
HighSandbox Evasion Gated Capabilitydist/skills/browser/runtime/omowright/index.js
Affected versions and remediation
This report applies to oh-my-opencode@5.1.4.
See all versions of oh-my-opencode for other recorded verdicts.
- Review the evidence and your use of oh-my-opencode@5.1.4 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.