psyclaw@0.30.19
A standalone, evidence-grounded social-science research agent with research contracts, evidence gates, and recoverable workflows
AI Security Review
scanned 17d ago · by lpm-firewall-aiSource inspection found no automatic install hook or concrete attack behavior. The flagged agent setup, credential-file reads, and test helper have product-aligned or user-controlled behavior in the inspected paths.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
No malicious trigger was identified; relevant setup behavior requires an explicit CLI or interface action.
Impact
No confirmed attack impact was established.
Mechanism
No source evidence showed credential transfer, unconsented agent configuration changes, or automatic install-time mutation.
AI rationale
Source inspection found no automatic install hook or concrete attack behavior. The flagged agent setup, credential-file reads, and test helper have product-aligned or user-controlled behavior in the inspected paths.
Decision evidence
public snapshotAI called this Clean at 92.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json lists prepublishOnly for branding and build tasks; the inspected scripts contain no preinstall, install, or postinstall hook.
- The plugin manager installs a selected row after an install action and persists it locally; the panel reads auth.json while detecting configured providers.
- User-skill discovery includes standard project skill directories, and its local-skill install API validates and copies a caller-supplied directory.
- The flagged test configuration contains a helper that normalizes timestamps in dictionaries and lists.
- The TUI requires a y confirmation before running an agent install; recommended-skill code resolves requested IDs through its catalog and restricts sources to GitHub.
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@0.30.19.
See all versions of psyclaw for other recorded verdicts.
- Review the evidence and your use of psyclaw@0.30.19 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.