@skillsmith/cli@0.8.8
A registry for sharing, scanning, and tracking agent skills across teams.
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe source shows an explicit, opt-in agent hook installer rather than an automatic lifecycle mutation. Its persistent agent configuration and telemetry behavior fit a guarded capability warning.
Decision evidence
public snapshot- The package exposes a CLI entry point and has no npm install lifecycle hook.
- An explicit telemetry command can install a Claude Code Skill hook into user or project settings.
- The installer copies its telemetry script and writes the resulting hook settings.
- The hook exits unless local telemetry is enabled and sends a limited invocation payload to its configured endpoint.
- The telemetry hook can persist as an AI-agent configuration change after an explicit user command.
- The install command permits overriding the telemetry endpoint.
Source & flagged code
6 flaggedManifest-reachable source sends a prompted API credential to a fixed unofficial gateway and persists the redirection.
dist/cli.jsView on unpkgSource gates dangerous network, credential, or execution behavior behind CI, host, platform, time, or geo fingerprint checks.
Findings
Affected versions and remediation
This report applies to @skillsmith/cli@0.8.8.
See all versions of @skillsmith/cli for other recorded verdicts.
- Review the evidence and your use of @skillsmith/cli@0.8.8 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.