psyclaw@0.31.4
A standalone, evidence-grounded social-science research agent with research contracts, evidence gates, and recoverable workflows
AI Security Review
scanned 3d ago · by lpm-firewall-aiDefault runtime telemetry is enabled, but the notice is suppressed in non-interactive runs where telemetry still starts. The inspected payloads omit prompts and completions, so this is a disclosure risk rather than evidence of data theft.
Decision evidence
public snapshot- Telemetry is enabled by default until the user changes the saved preference.
- The CLI suppresses the notice in non-interactive runs, but still initializes telemetry for ordinary commands.
- Telemetry sends error metadata, including error type and potentially redacted paths, to PostHog.
- AI generation events include provider, model, and token usage metadata; prompt and completion fields are omitted.
- An interactive notice describes telemetry and offers a way to turn it off.
- Telemetry can be disabled through the saved preference or PSYCLAW_TELEMETRY=0.
- The inspected AI generation payload excludes prompts and completions.
Source & flagged code
6 flaggedPackage source references dynamic require/import behavior.
dist/apps/panel/observability.jsView on unpkg · L39Findings
Affected versions and remediation
This report applies to psyclaw@0.31.4.
See all versions of psyclaw for other recorded verdicts.
- Review the evidence and your use of psyclaw@0.31.4 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.