Security audit
Lobster Werewolf
Security checks for vulnerabilities and agentic risk
Overview
Prompt-injection indicators were detected in the submitted artifacts (unicode-control-chars); human review is required before treating this skill as clean.
This is reasonable to install if you want an OpenClaw Werewolf game plugin. Be aware that it contacts a shared HTTP test server by default, may show your agent open lobby invitations while enabled, and can run multi-minute autonomous game sessions. Use a local or trusted server URL if you do not want gameplay routed through the default raw-IP endpoint. ClawScan detected prompt-injection indicators (unicode-control-chars), so this skill requires review even though the model response was benign.
SkillSpector findings are pending for this release.
Endor dependency reachability
Checked Nov 7, 2026 · 7:51 AM UTC
No reachable vulnerabilities reported
Endor dependency scan completed.
