psyclaw@0.30.0
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-aiThe package has an explicit user-triggered agent-runtime mutation surface but no automatic registry-install hook or concrete malicious behavior. Downgrade to a warning for its guarded first-party extension lifecycle risk.
Decision evidence
public snapshot- Running the CLI automatically patches the bundled Pi runtime and configures its agent directory.
- The rebrand routine rewrites several files in the bundled agent dependency, including command and settings components.
- The TUI can execute an agent install only after an interactive Y confirmation.
- The manifest has no preinstall, install, or postinstall hook; its only lifecycle hook is prepublishOnly.
- The flagged Python file is a conventional pytest fixture and contains no payload behavior.
- No secret exfiltration, self-dependency, or unconsented install-time network execution was found.
Source & flagged code
6 flaggedPackage source references dynamic require/import behavior.
dist/apps/panel/observability.jsView on unpkg · L38Findings
Affected versions and remediation
This report applies to psyclaw@0.30.0.
See all versions of psyclaw for other recorded verdicts.
- Review the evidence and your use of psyclaw@0.30.0 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.