google-agents-cli-publish
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [Data Processing Surface]: The skill involves reading local project files, such as
deployment_metadata.json,uv.lock, andtoolspec.json, to automate registration and check for environment compatibility. While standard for development workflows, these files represent a point where external data is ingested into the agent's context. - Ingestion points:
deployment_metadata.json,toolspec.json,uv.lock(referenced in SKILL.md). - Boundary markers: None explicitly defined within the instructions.
- Capability inventory: Shell command execution via
agents-cliandgcloud, network communication with Google Cloud APIs. - Sanitization: The skill assumes the integrity of the local development environment and project files.
- [Tool Integration]: The skill utilizes the
agents-cliandgcloudcommand-line interfaces to perform management tasks. These operations are aligned with the skill's intended purpose of managing agent lifecycles on Google Cloud infrastructure.
Audit Metadata