Caveat verdict
wolverine
wolverine-ai
45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.
The skill's use of package installation and AI-driven process management may introduce security risks if not properly validated and secured.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
90
security
60
transparency
70
maintenance
Permission integrity
Installs packages at runtime — transitive dependencies are not auditable
package_install
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: ANTHROPIC_API_KEY). Requires 1 system binary. (1 elevated: npm).
package_install Is this flag fair?
Thanks — recorded.