Caveat verdict
agentconnex-register
The skill seems to provide a legitimate service for auto-registering OpenClaw agents on AgentConnex and does not contain malicious behavior.
⚠ 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.
Findings (4)
Instructs covert action — may act without user awareness
scripts/auto-boot.js · prose · downgraded · silently
Sets world-executable permissions
SKILL.md · code · chmod 700
Node http/https module — low-level network access
scripts/auto-boot.js · prose · downgraded · require('https')
Accesses sensitive environment variables
scripts/heartbeat-sync.js · prose · downgraded · process.env.AGENTCONNEX_API_KEY
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.