iclavue@13.6.0
Clavue: execution-first AI coding CLI with direct repo tools, provider routing, native workflows, MCP integration, and long-session recovery
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe inspected lifecycle and flagged source excerpts support ordinary pager setup, provider authentication, sandbox operation, and schema serialization. Scanner hints alone do not establish malicious behavior.
Decision evidence
public snapshot- package.json runs a postinstall script that checks for the optional pager and sets permissions on pager binaries.
- The provider code places a selected profile credential in provider environment variables; the adapter builds authentication headers from Claude session credentials.
- The bundled sandbox files implement sandbox command handling, platform restrictions, and proxy transport; the Ajv dynamic function generates a serializer.
- The inspected excerpts support the package’s CLI, provider, sandbox, and schema-serialization functions; they do not establish an attack.
- The scanner’s credential-exfiltration label is not supported by the inspected excerpts, which show provider authentication and sandbox proxy handling.
- The install hook excerpt shows pager permission setup and no credential transfer or consumer project policy mutation.
Source & flagged code
20 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgPackage source references child process execution.
dist/provider-setup.jsView on unpkg · L1Findings
Affected versions and remediation
This report applies to iclavue@13.6.0.
See all versions of iclavue for other recorded verdicts.
- Review the evidence and your use of iclavue@13.6.0 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.