psyclaw@0.30.8
A standalone, evidence-grounded social-science research agent with research contracts, evidence gates, and recoverable workflows
AI Security Review
scanned 27d ago · by lpm-firewall-aiThe manifest and required source excerpts show no install-time attack. The flagged agent-related code supports interactive plugin management and provider discovery, with no inspected evidence of secret forwarding or unconsented configuration changes.
Static reason
No blocking static signals were detected.
Trigger
Using the CLI or interactive plugin manager; no npm install hook was found.
Impact
No confirmed credential theft, unconsented agent configuration mutation, or other attack effect was established.
Mechanism
The inspected plugin flow validates the selected row and source reference before calling its installer. The panel reads auth files to determine which providers are configured.
AI rationale
The manifest and required source excerpts show no install-time attack. The flagged agent-related code supports interactive plugin management and provider discovery, with no inspected evidence of secret forwarding or unconsented configuration changes.
Decision evidence
public snapshotAI called this Clean at 78.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json exposes the CLI through scripts/psyclaw.mjs; its only publication hook is prepublishOnly, with no install lifecycle hook.
- The recommended plugin installer checks installability and source presence before proceeding; the inspected flow is user initiated through the plugin manager.
- The panel reads agent auth files to identify configured provider names; the inspected code does not show credential values being sent elsewhere.
- User skill roots include host agent directories, supporting skill discovery rather than an install-time configuration change.
- The flagged Python file is pytest fixture setup, and the TUI excerpt shows a command runner used by the app.
Evidence against
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsTelemetryUrlStrings
Source & flagged code
5 flaggeddist/apps/panel/observability.jsView file
39async function loadEsm(url) {
L40: return import(url);
L41: }
Medium
Dynamic Require
Package source references dynamic require/import behavior.
dist/apps/panel/observability.jsView on unpkg · L39vendor/windows/x64/fd.exeView file
•path = vendor/windows/x64/fd.exe
kind = native_binary
sizeBytes = 4104192
magicHex = [redacted]
Medium
vendor/ars/tools/release-discipline/scripts/sync-toolkit.shView file
Findings
2 High6 Medium6 Low
HighPayload In Excluded Dirvendor/ars/scripts/adapters/tests/conftest.py
HighSemantic Analysis Limiteddist/src/tui/app.js#virtual:normalized:round1
MediumDynamic Requiredist/apps/panel/observability.js
MediumNetwork
MediumEnvironment Vars
MediumShips Native Binaryvendor/windows/x64/fd.exe
MediumShips Build Helpervendor/ars/tools/release-discipline/scripts/sync-toolkit.sh
MediumStructural Risk Force Deep Review
LowNon Install Lifecycle Scripts
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowTelemetry
LowUrl Strings
Affected versions and remediation
This report applies to psyclaw@0.30.8.
See all versions of psyclaw for other recorded verdicts.
- Review the evidence and your use of psyclaw@0.30.8 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.