psyclaw@0.30.9
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-aiSource inspection found no malicious behavior. Agent plugin setup is user-invoked and project-scoped, the high flagged Python file contains test fixtures, and provider auth files are read for provider discovery without an inspected forwarding path.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
An interactive plugin manager, panel action, or TUI install confirmation invoked by the user.
Impact
No confirmed malicious effect or credential exposure was established by the inspected source.
Mechanism
The extension installs a selected plugin locally, and the panel exposes plugin installation through its UI; the inspected credential-reading code only discovers configured providers.
AI rationale
Source inspection found no malicious behavior. Agent plugin setup is user-invoked and project-scoped, the high flagged Python file contains test fixtures, and provider auth files are read for provider discovery without an inspected forwarding path.
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json has no preinstall, install, or postinstall hook; its prepublishOnly hook runs branding and build checks.
- The Pi extension installs a recommended plugin only through its interactive plugin manager, into the current project, and then asks the user to reload it.
- The panel reads auth files to identify configured providers; the inspected code parses provider keys and values but shows no credential forwarding.
- User skill roots include project agent skill directories, consistent with the package’s skill-management behavior.
- The flagged conftest.py contains pytest fixtures and path helpers, not an executable payload.
- The TUI requires an explicit install confirmation, and panel plugin installation is wired to an invoked panel action.
Evidence against
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
Source & flagged code
6 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
3 High6 Medium6 Low
HighPayload In Excluded Dirvendor/ars/scripts/adapters/tests/conftest.py
HighSemantic Analysis Limiteddist/src/tui/app.js#virtual:normalized:round1
HighPrevious Version Dangerous Deltadist/src/panel/workbench.js
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
Low
Affected versions and remediation
This report applies to psyclaw@0.30.9.
See all versions of psyclaw for other recorded verdicts.
- Review the evidence and your use of psyclaw@0.30.9 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.