ops-yolo
What this skill does
The skill 'ops-yolo' is designed to simulate a high-level operational analysis by spawning multiple C-suite agents and autonomously running business operations for a day when the user types 'YOLO'. It
github/davepoon - Data Exfiltration Risk - 3.3k stars
Threat analysis
Skill info
pkg:github/davepoon/buildwithclaude@faa769d?skill=ops-yoloAssessments (3)
Data Exfiltration Risk
Data Exfiltration Risk via local-llm-review
SKILL.md
The skill references loading secrets from multiple sources (env → Doppler → password manager) including GITHUB_TOKEN, SENTRY_AUTH_TOKEN, LINEAR_API_KEY, and AWS_ACCESS_KEY_ID. These are sensitive credUnrestricted Agent Autonomy
Unrestricted Agent Autonomy via local-llm-review
SKILL.md
The skill includes the instruction 'autonomously run the business for a day using /loop' which implies the agent can execute actions without direct user oversight, potentially leading to unintended orOverly Broad Tool Access
Overly Broad Tool Access via local-llm-review
SKILL.md
The skill has access to a wide range of tools, including 'TaskCreate', 'CronCreate', 'WebFetch', and 'WebSearch', which could be used to perform actions beyond the user's intent if not properly constrBadge
Add the Anomity scan badge for ops-yolo 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 ops-yolo? Report an issue or request a rescan.
