@slopus/rig@0.0.7
Opinionated pi fork with strong defaults for coding-agent workflows.
AI Security Review
scanned 3mo ago · by lpm-firewall-aiThe flagged primitives are consistent with an explicitly invoked coding-agent CLI: provider authentication, clipboard image attachment, sandboxed shell execution, and local configuration/trust storage. Inspection found no lifecycle execution or concrete chain that exfiltrates data, installs persistence, or mutates foreign agent controls.
Decision evidence
public snapshot- `dist/app/readClipboardImage.js` reads clipboard images only during runtime and writes them to a rig temp directory.
- `dist/providers/readClaudeCodeOAuthToken.js` reads a Claude OAuth token for the selected provider.
- `package.json` has no preinstall, install, or postinstall lifecycle hook.
- `dist/main.js` runs only when the `rig` CLI is explicitly invoked.
- `dist/agent/context/assertCanReadPath.js` blocks sensitive files outside the workspace in restricted modes.
- `dist/config/createProjectConfigSecurityNotice.js` ignores project-requested permission escalation.
- `dist/mcp/createProjectMcpSecurityNotice.js` requires one-time trust for project MCP servers.
- No source evidence of stealth exfiltration, remote payload execution, destructive actions, or foreign AI-agent config mutation.
Source & flagged code
4 flagged · loading sourcePackage source references dynamic require/import behavior.
dist/app/readClipboardImage.jsView on unpkg · L70Package source references weak cryptographic algorithms.
dist/tools/utils/prepareImageForClaude.jsView on unpkg · L5Findings
Affected versions and remediation
This report applies to @slopus/rig@0.0.7.
See all versions of @slopus/rig for other recorded verdicts.
- Review the evidence and your use of @slopus/rig@0.0.7 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.