orlithra-coding-agent@0.0.33
Secure coding agent CLI with session management
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe runtime forwards a model API key to a configurable gateway, creating conditional credential exposure if the destination is unintended. The inspected source does not establish a hidden transfer or a malicious default recipient, so this warrants a warning rather than a block.
Decision evidence
public snapshot- The CLI entrypoint loads the packaged runtime.
- The model stream passes its API key as a bearer token to a gateway whose URL can be set through an environment variable, defaulting to api.orlithra.com.
- The gateway request sends that bearer token in an Authorization header.
- The manifest shows a prepublishOnly build hook, not an install-time hook.
- The inspected source establishes conditional credential forwarding but does not establish that the default gateway is malicious or that forwarding is hidden.
Source & flagged code
10 flagged · loading sourceThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/bundle/chunk-RGQHZUTR.jsView on unpkgPackage source references child process execution.
dist/bundle/chunk-RGQHZUTR.jsView on unpkg · L2588Findings
Affected versions and remediation
This report applies to orlithra-coding-agent@0.0.33.
See all versions of orlithra-coding-agent for other recorded verdicts.
- Review the evidence and your use of orlithra-coding-agent@0.0.33 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.