psyclaw@0.30.2
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 inspected code does not establish malicious behavior or an install-time attack chain. It warrants a warning because it ships agent extensions and user-invoked installation and runtime-network capabilities, with incomplete analysis coverage.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
A user launches PsyClaw and confirms an installation, or launches its runtime with the preload environment flag.
Impact
A user-approved action can install agent-related tools; no unconsented attack behavior was confirmed.
Mechanism
Agent extensions invoke selected install commands and optionally configure routed network access.
AI rationale
The inspected code does not establish malicious behavior or an install-time attack chain. It warrants a warning because it ships agent extensions and user-invoked installation and runtime-network capabilities, with incomplete analysis coverage.
Evidence
package.jsondist/src/tui/app.jsdist/src/network-routing.js
Decision evidence
public snapshotAI called this Suspicious at 78.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The manifest registers three Pi extensions, creating an agent-extension runtime surface.
- The interactive TUI runs an installer command after the user confirms with Y.
- A gated runtime preload changes network handling and ensures two search tools are present.
- The high-severity Python finding is ordinary pytest fixture code, not a hidden payload.
Evidence against
- package.json has no preinstall, install, or postinstall hook.
- The TUI requires an explicit confirmation before invoking its installer.
- No credential exfiltration, destructive install-time action, or self-dependency was found in the inspected files.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsTelemetryUrlStrings
Source & flagged code
6 flaggeddist/apps/panel/observability.jsView file
38async function loadEsm(url) {
L39: return import(url);
L40: }
Medium
Dynamic Require
Package source references dynamic require/import behavior.
dist/apps/panel/observability.jsView on unpkg · L38vendor/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/network-routing.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@0.30.2.
See all versions of psyclaw for other recorded verdicts.
- Review the evidence and your use of psyclaw@0.30.2 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.