psyclaw@0.30.7
A standalone, evidence-grounded social-science research agent with research contracts, evidence gates, and recoverable workflows
AI Security Review
scanned 2mo ago · by lpm-firewall-aiStatic inspection found no npm install hook or self-dependency chain. The flagged test fixture is benign, and command execution requiring user interaction is consistent with the package's agent-management function.
Decision evidence
public snapshot- The manifest has no install lifecycle hook; its only lifecycle-like script is prepublishOnly.
- The high-severity Python finding is ordinary pytest fixture code, not a hidden payload.
- The CLI rebrands its bundled runtime only when the user runs the psyclaw command.
- Agent installation is gated by an interactive confirmation and a y keystroke.
- The CLI modifies files in its bundled Pi dependency during explicit execution.
- Telemetry is enabled by default and uses package-aligned observability services.
- A Windows executable is shipped, but no source path inspected automatically launches it.
Source & flagged code
5 flaggedPackage source references dynamic require/import behavior.
dist/apps/panel/observability.jsView on unpkg · L39Findings
Affected versions and remediation
This report applies to psyclaw@0.30.7.
See all versions of psyclaw for other recorded verdicts.
- Review the evidence and your use of psyclaw@0.30.7 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.