Shell command execution detected (child_process).
- Code
- suspicious.dangerous_exec
- Location
- index.js:268
Security audit
Security checks across malware telemetry and agentic risk
The skill is mostly a disclosed agent self-evolution tool, but it includes default-on background credit-spending behavior that is under-disclosed for a normal install.
Install only if you want a persistent EvoMap-connected agent-evolution system. Before running with A2A_HUB_URL or a node identity configured, decide whether ATP auto-spend is acceptable; disable it with EVOLVER_ATP_AUTOBUY=off or evolver atp disable, and review caps, hook installation, validator participation, and GitHub token usage.
SkillSpector could not complete.
1/63 vendors flagged this skill as malicious, and 62/63 flagged it as clean.
Detected: suspicious.dangerous_exec, suspicious.dynamic_code_execution, suspicious.env_credential_access (+4 more)