agent-platform-deploy
What this skill does
Deployment of models from Model Garden to Agent Platform endpoints, including copying and deploying 1P Tuned Models
github/google - Privilege Escalation - 17.6k stars
Threat analysis
Skill info
pkg:github/google/skills@ab92ce1?skill=agent-platform-deployAssessments (1)
Privilege Escalation
Privilege Escalation via local-llm-review
scripts/config_gcloud_cli.sh
The script sets up a gcloud configuration with a specified project, region, and user email. It activates a configuration named "${ENV}-cdmodel" and sets the project, region, and account. This could beBadge
Add the Anomity scan badge for agent-platform-deploy 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 agent-platform-deploy? Report an issue or request a rescan.
