psyclaw@0.29.16
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 is not shown to be malware, but its normal CLI path modifies an agent runtime and registers extensions. This warrants a warning for agent-extension lifecycle risk rather than a publish block.
Decision evidence
public snapshot- The CLI runs a runtime rebranding routine before loading the main program.
- That routine rewrites selected files in its bundled coding-agent runtime and hides underlying login commands.
- The package declares Pi extensions, creating an agent-extension control surface.
- The flagged MCP code requires enabled, trusted configuration before discovery.
- The flagged Python file is a pytest fixture module, not an executable payload.
- There is no preinstall, install, or postinstall lifecycle hook.
- No self-dependency is declared.
- No credential harvesting or unconsented network exfiltration was found.
- The runtime mutation is user-invoked and targets the package's bundled Pi dependency.
Source & flagged code
6 flaggedPackage source references dynamic require/import behavior.
dist/src/network-routing.jsView on unpkg · L170Findings
Affected versions and remediation
This report applies to psyclaw@0.29.16.
See all versions of psyclaw for other recorded verdicts.
- Review the evidence and your use of psyclaw@0.29.16 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.