psyclaw@0.30.15
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-aiInspected source supports a clean verdict: the package has no npm install hook, and the relevant installation behavior is activated through user-facing actions. The scanner flags map to benign test setup or package functionality; no concrete attack surface was established.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
A user selects an install action in the plugin manager or approves an installation in the TUI.
Impact
No confirmed unauthorized mutation, credential exfiltration, or other attack impact was established.
Mechanism
The package stages a recommended skill locally; the inspected panel code reads authentication files only to determine configured providers.
AI rationale
Inspected source supports a clean verdict: the package has no npm install hook, and the relevant installation behavior is activated through user-facing actions. The scanner flags map to benign test setup or package functionality; no concrete attack surface was established.
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest identifies PsyClaw as a research agent and has no npm install lifecycle hook; its only publish hook is prepublishOnly.
- The plugin installation function checks that a user-selected item is installable before installing it.
- The panel reads agent authentication files to identify configured providers; this code does not send their contents.
- User skill discovery includes project and host-agent skill directories.
- The flagged Python file is test fixture configuration that defines repository paths and shared fixtures.
- The TUI invokes installation through an explicit runInstall call with approval recorded.
- Recommended skill installation stages and copies a selected skill into its destination.
Evidence against
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
HighEntropyStrings
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@0.30.15.
See all versions of psyclaw for other recorded verdicts.
- Review the evidence and your use of psyclaw@0.30.15 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.