@ory/claude-agent-sdk@1.7.0
Ory Agent Security for the Anthropic Claude Agent SDK — per-tool authorization, activity auditing, and identity propagation via PreToolUse hooks and canUseTool. Built on @ory/argus.
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe package enables a dependency’s install-time telemetry, which reads identifying Git configuration data and sends it to a fixed external endpoint. This is install-time user data exfiltration, so the package should be blocked.
Decision evidence
public snapshot- The package enables reova telemetry and configures https://telemetry.reo.dev/data.
- The reova dependency has a postinstall hook that starts its tracker.
- The tracker reads the installer’s email from ~/.gitconfig and extracts its domain.
- The install payload includes that email domain and is POSTed to the configured endpoint.
Source & flagged code
8 flaggedThe package enables reova telemetry and configures https://telemetry.reo.dev/data.
package.jsonView on unpkg · L11The reova dependency has a postinstall hook that starts its tracker.
.lpm-dependency-evidence-35911440-4e11-40b5-a9b7-7e922233b974/1/npm-linux/package.jsonView on unpkg · L6Findings
Affected versions and remediation
This report applies to @ory/claude-agent-sdk@1.7.0.
See all versions of @ory/claude-agent-sdk for other recorded verdicts.
- Avoid installing @ory/claude-agent-sdk@1.7.0. Remove it from direct dependencies and check your lockfile for transitive copies.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
- If this version ran, investigate the affected machine and build environment. Rotate credentials it could access and rebuild from a trusted environment.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.