psyclaw@0.30.17
A standalone, evidence-grounded social-science research agent with research contracts, evidence gates, and recoverable workflows
AI Security Review
scanned 22d ago · by lpm-firewall-aiThe manifest has no install-time lifecycle hook, and the reviewed agent and installation behaviors are user-invoked or limited to local provider detection. The scanner’s structural hints did not establish malicious behavior in the inspected source.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
The package has no npm install-time hook; its prepublishOnly script runs branding checks and a build.
Impact
No unauthorized credential transfer, automatic agent configuration change, or other concrete attack was established.
Mechanism
The inspected plugin setup follows an explicit manager selection, agent credentials are read for provider detection, and TUI installation requires confirmation.
AI rationale
The manifest has no install-time lifecycle hook, and the reviewed agent and installation behaviors are user-invoked or limited to local provider detection. The scanner’s structural hints did not establish malicious behavior in the inspected source.
Decision evidence
public snapshotAI called this Clean at 94.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json defines only a prepublishOnly lifecycle script, which runs branding checks and a build.
- Plugin installation checks that an item is installable and has a source, then proceeds only after the user selects an install action in the plugin manager.
- The panel reads local agent authentication files to identify configured providers; the inspected code uses provider keys for detection.
- User skill discovery includes explicit project and host-agent skill directories.
- The adapter fixture file defines test paths and timestamp-cleaning helpers.
- The TUI requires a user action to enter install or import confirmation, and the recommended-skill installer uses Git for its catalog source.
Evidence against
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsTelemetry
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/skills/recommended.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@0.30.17.
See all versions of psyclaw for other recorded verdicts.
- Review the evidence and your use of psyclaw@0.30.17 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.