oh-my-opencode@5.1.7
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-aiInspected source supports a warning for explicit agent configuration that weakens permission safeguards. It does not establish malicious behavior warranting a publication block.
Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review
Trigger
Run CLI install or setup with Codex selected without disabling autonomous configuration.
Impact
Subsequent agent sessions can perform actions with fewer permission safeguards.
Mechanism
Write Codex config.toml with approval disabled, unrestricted filesystem access, suppressed warnings, enabled plugins, and trusted hooks.
AI rationale
Inspected source supports a warning for explicit agent configuration that weakens permission safeguards. It does not establish malicious behavior warranting a publication block.
Evidence
dist/cli-node/index.jsconfig.toml
Decision evidence
public snapshotAI called this Suspicious at 96.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- Explicit Codex setup enables autonomous permissions by default unless disabled.
- The Codex installer passes this setting to its configuration updater.
- Autonomous configuration disables approval prompts and selects unrestricted filesystem access.
- The same configuration suppresses full-access and world-writable warnings.
- Setup enables package plugins, trusts their hooks, and persists Codex configuration.
Evidence against
- The inspected npm postinstall performs platform checks and package-specific cache cleanup, rather than Codex configuration setup.
- Codex setup is activated by an explicit CLI install command and offers --no-codex-autonomous.
- The flagged shell-script locations are rejection-test inputs; the flagged bundle locations copy bundled MCP runtimes.
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@5.1.7.
See all versions of oh-my-opencode for other recorded verdicts.
- Review the evidence and your use of oh-my-opencode@5.1.7 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.