oh-my-opencode@5.1.14
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 agent configuration changes that substantially weaken execution safeguards. It does not substantiate the scanner's malicious verdict or a publish-blocking attack chain.
Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review
Trigger
Running the CLI install or setup command with Codex selected and autonomous mode enabled, which is the default.
Impact
Later agent actions can execute with reduced containment and fewer user approval barriers.
Mechanism
The installer writes Codex configuration that disables approvals, grants full filesystem access, removes network restrictions, and hides access warnings.
AI rationale
Source supports a warning for explicit agent configuration changes that substantially weaken execution safeguards. It does not substantiate the scanner's malicious verdict or a publish-blocking attack chain.
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 explicit CLI installer invokes Codex setup when Codex is selected.
- Codex autonomous mode defaults to enabled unless explicitly overridden.
- Autonomous setup sets approval_policy to never and sandbox_mode to danger-full-access, removes network restrictions, and hides the full-access warning.
- The installer writes these settings to Codex config.toml and enables package plugins, trusted hooks, and agent configurations.
- The npm postinstall hook performs platform checks and package-specific cache cleanup; inspected source does not establish an automatic agent configuration attack.
Evidence against
- The configuration mutation occurs through explicit CLI setup, with an option to preserve existing permission settings.
- Flagged agent configuration script locations are rejection-test inputs, and the inspected dynamic execution sink in dist/index.js compiles schema validation code.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsEval
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@5.1.14.
See all versions of oh-my-opencode for other recorded verdicts.
- Review the evidence and your use of oh-my-opencode@5.1.14 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.