oh-my-opencode@5.1.5
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 persistent permission expansion through explicit CLI setup, warranting a capability warning under the supplied policy. It does not establish a block-eligible malicious installation chain.
Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review; previous stored version diff introduced dangerous source
Trigger
Running CLI setup with Codex selected and autonomous permissions not disabled.
Impact
Later agent sessions can operate with full filesystem access without approval prompts.
Mechanism
The installer enables autonomous permissions by default, replaces approval and sandbox settings, and writes the resulting Codex configuration.
AI rationale
Source establishes persistent permission expansion through explicit CLI setup, warranting a capability warning under the supplied policy. It does not establish a block-eligible malicious installation chain.
Evidence
dist/cli/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 replaces approval policy with never and sandbox mode with danger-full-access.
- Selecting Codex installation enables autonomous permissions by default unless explicitly overridden.
- The installer targets config.toml under the resolved Codex home and persists the modified configuration.
- The CLI invokes this installer when Codex setup is selected.
- The npm postinstall hook runs a separate script whose cache deletion is restricted to this package's named cache entries.
Evidence against
- The inspected configuration mutation occurs through CLI setup, rather than npm postinstall.
- The autonomous permission setting supports an explicit false override.
- The flagged shell locations are rejection tests; the flagged bundle locations copy bundled MCP runtimes into plugin directories.
- No concrete credential theft or malicious payload execution was established.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsEval
Source & flagged code
24 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
5 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
CriticalPrevious Version Dangerous Deltadist/index.js
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
Affected versions and remediation
This report applies to oh-my-opencode@5.1.5.
See all versions of oh-my-opencode for other recorded verdicts.
- Review the evidence and your use of oh-my-opencode@5.1.5 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.