oh-my-opencode@5.1.6
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 supports a warning for explicit setup that grants broad agent permissions by default. It does not establish malicious intent or a block-eligible install lifecycle attack.
Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review
Trigger
User invokes CLI setup with Codex selected.
Impact
Subsequent agent execution has reduced approval and filesystem restrictions.
Mechanism
The installer writes Codex configuration, enables plugins, trusts hooks, and applies autonomous permissions unless overridden.
AI rationale
Source supports a warning for explicit setup that grants broad agent permissions by default. It does not establish malicious intent or a block-eligible install lifecycle attack.
Evidence
dist/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 Codex installer changes approval policy to never and sandbox mode to danger-full-access.
- Codex autonomous permissions default to enabled unless explicitly overridden.
- The installer updates config.toml with plugin, trusted hook, agent, and autonomous permission settings.
- The configuration writer enables package plugins and trusts their hooks.
- Codex configuration changes are activated by the CLI installation flow.
Evidence against
- The inspected npm postinstall performs package-specific cache invalidation and binary checks, rather than broad agent configuration writes.
- The flagged shell script locations contain request-context rejection tests.
- The flagged bundle locations copy bundled MCP runtimes into the package plugin installation.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsEvalFilesystemNetworkShell
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@5.1.6.
See all versions of oh-my-opencode for other recorded verdicts.
- Review the evidence and your use of oh-my-opencode@5.1.6 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.