oh-my-opencode@5.1.44
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 13d ago · by lpm-firewall-aiThe postinstall hook makes a recursive cache deletion without a visible consent check, so I classify this as a limited destructive capability warranting a warning. The flagged test evaluation and LSP similarity match do not establish malicious behavior.
Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review
Trigger
Installing the package through npm.
Impact
Matching cached plugin copies are removed and may need to be restored or refreshed.
Mechanism
The postinstall hook scans the OpenCode cache directories and recursively deletes directories with names matching either listed package prefix.
AI rationale
The postinstall hook makes a recursive cache deletion without a visible consent check, so I classify this as a limited destructive capability warranting a warning. The flagged test evaluation and LSP similarity match do not establish malicious behavior.
Evidence
package.jsonpostinstall.mjs
Decision evidence
public snapshotAI called this Suspicious at 72.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The `postinstall` hook runs automatically after installation.
- The hook recursively removes matching plugin cache directories under the user’s OpenCode cache.
- The removal is limited to directories whose names begin with the two listed plugin package names.
Evidence against
- The flagged dynamic code evaluation is in a test that builds a selector rule from a local fixture.
- The source-similarity match is in an LSP cancellation test file.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsEvalFilesystemNetworkShell
HighEntropyStringsMinifiedTelemetryUrlStrings
GitDependency
Source & flagged code
22 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 Critical13 High9 Medium6 Low
CriticalSame File Env Network Executiondist/skills/browser/runtime/omowright/index.js
CriticalDownload Executedist/skills/browser/runtime/omowright/index.js
CriticalEncrypted Payload Temp Executiondist/cli-node/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@5.1.44.
See all versions of oh-my-opencode for other recorded verdicts.
- Review the evidence and your use of oh-my-opencode@5.1.44 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.