openclaw-boss
What this skill does
User profile analysis and performance review with a 'boss' tone, generating reports based on conversation history.
github/leoyeai - Persistence - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=openclaw-bossAssessments (4)
Persistence
Persistence via local-llm-review
scripts/weekly-profile.sh
Creating cron jobs for weekly and monthly reports that execute Python scripts with no user opt-out or sandboxingPersistence via local-llm-review
scripts/monthly-profile.sh
Creating cron jobs for monthly reports that execute Python scripts with no user opt-out or sandboxingData Exfiltration
Data Exfiltration via local-llm-review
scripts/analyze-user.py
Reading sensitive files from /root/.openclaw/workspace/ including MEMORY.md, USER.md, and memory/*.md without explicit user consent or encryptionPrivilege Escalation
Privilege Escalation via local-llm-review
.onload
Creating cron jobs in /etc/cron.d/ with root privileges without user confirmation or sandboxingBadge
Add the Anomity scan badge for openclaw-boss to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of openclaw-boss? Report an issue or request a rescan.
