gemini
What this skill does
Provides access to Google's Gemini 3 Pro model through the Gemini CLI for code analysis, plan reviews, and big context processing.
github/softaworks - Process Management - 2.3k stars
Threat analysis
Skill info
pkg:github/softaworks/agent-toolkit@3027f20?skill=geminiAssessments (2)
Process Management
Process Management via local-llm-review
SKILL.md
The skill provides instructions for killing processes using `pkill -9 -f "gemini.*gemini-3-pro-preview"` which could be used to terminate arbitrary processes if misconfigured or exploited.Automation Risks
Automation Risks via local-llm-review
SKILL.md
The skill recommends using `--approval-mode yolo` for automated execution, which could be considered a risk if not properly secured as it bypasses approval prompts.Badge
Add the Anomity scan badge for gemini 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 gemini? Report an issue or request a rescan.
