migrate-v2-to-v3
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various local shell commands, including
terraform,tofu,uv,rg(ripgrep),jq, andrsync. These commands are used to audit configurations, generate plans, and apply infrastructure changes within the user's project directory. - [DATA_EXFILTRATION]: The skill interacts with sensitive infrastructure data by performing a
terraform state pull, which exports the cluster's state (often containing secrets and sensitive resource metadata) to a local JSON file for backup. It also evaluates and manages SSH authorized keys on the cluster nodes. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided configuration files and plan outputs, creating a vulnerability surface where malicious content in those files could influence the agent's behavior.
- Ingestion points: The agent reads local Terraform source files (
.tf) and JSON-formatted plan outputs (v3-upgrade-plan.json) during the audit and migration workflow. - Boundary markers: The skill does not employ explicit delimiters or system instructions to protect the agent from instructions embedded within the configuration files it reads.
- Capability inventory: The agent has the capability to execute administrative shell commands and perform infrastructure changes via
terraform apply. - Sanitization: There are no explicit steps to sanitize or validate the content of the configuration files before the agent processes and acts upon their contents.
Audit Metadata