psyclaw@0.29.13
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 package performs explicit-user-command mutation of an AI-agent runtime, which is a real capability risk. There is no evidence of automatic install-time execution or a concrete malicious payload.
Static reason
No blocking static signals were detected.; source matched previously finalized malicious package; routed for review; previous stored version diff introduced dangerous source
Trigger
The user runs the psyclaw executable.
Impact
It can alter Pi configuration, interactive behavior, settings defaults, and available slash commands for Psyclaw's runtime.
Mechanism
Runtime patching of the bundled Pi agent dependency.
AI rationale
The package performs explicit-user-command mutation of an AI-agent runtime, which is a real capability risk. There is no evidence of automatic install-time execution or a concrete malicious payload.
Evidence
scripts/psyclaw.mjsscripts/rebrand-pi.mjspackage.jsonnode_modules/@earendil-works/pi-coding-agent/package.jsonnode_modules/@earendil-works/pi-coding-agent/dist/modes/interactive/interactive-mode.jsnode_modules/@earendil-works/pi-coding-agent/dist/core/settings-manager.jsnode_modules/@earendil-works/pi-coding-agent/dist/core/slash-commands.jsnode_modules/@earendil-works/pi-coding-agent/dist/utils/tools-manager.js
Decision evidence
public snapshotAI called this Suspicious at 88.0% confidence as Unknown with medium false-positive risk.
Evidence for warning
- Running the psyclaw executable silently invokes a runtime rebranding routine.
- That routine resolves the Pi dependency and changes several of its installed runtime files, including settings and commands.
- The package registers Pi extensions, skills, and prompts, creating an agent control surface.
Evidence against
- The manifest has no install, preinstall, or postinstall hook and no runtime dependency on psyclaw itself.
- The mutation occurs only after the user runs the psyclaw command.
- The inspected MCP transport uses argument arrays, disables shell use, and passes an explicit environment.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsProtestwareUrlStrings
Source & flagged code
7 flaggeddist/src/network-routing.jsView file
170const managerUrl = new URL("./utils/tools-manager.js", entryHref);
L171: const manager = await import(managerUrl.href);
L172: const failures = [];
Medium
Dynamic Require
Package source references dynamic require/import behavior.
dist/src/network-routing.jsView on unpkg · L170vendor/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
4 High7 Medium5 Low
HighPayload In Excluded Dirvendor/ars/scripts/adapters/tests/conftest.py
HighSemantic Analysis Limiteddist/src/tui/app.js#virtual:normalized:round1
HighKnown Malware Source Similaritydist/src/integrations/mcp.js
HighPrevious Version Dangerous Deltadist/src/cli.js
MediumDynamic Requiredist/src/network-routing.js
MediumNetwork
MediumEnvironment Vars
MediumProtestware
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
Affected versions and remediation
This report applies to psyclaw@0.29.13.
See all versions of psyclaw for other recorded verdicts.
- Review the evidence and your use of psyclaw@0.29.13 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.