Skills
skills/googlecloudplatform/cloud-run-mcp/cloud-run/Gen Agent Trust Hub

cloud-run

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the gcloud CLI to manage Cloud Run resources. This includes actions such as creating, updating, and deleting services and jobs.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface.
  • Ingestion points: Untrusted data enters the agent context through the output of commands like gcloud run logs read and gcloud run services describe in SKILL.md.
  • Boundary markers: The instructions do not specify boundary markers or include warnings to ignore instructions embedded in logs or configuration data.
  • Capability inventory: The skill facilitates extensive cloud management capabilities via gcloud in SKILL.md, including service modification, IAM policy changes (add-iam-policy-binding), and service proxying.
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the Cloud Run environment before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 03:58 PM
Security Audit — agent-trust-hub — cloud-run