tofu
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches configuration and installation scripts from the official OpenTofu domain (
get.opentofu.org). - [REMOTE_CODE_EXECUTION]: Provides instructions to download and execute remote scripts via
curl | shfor tool installation from a well-known project source. - [COMMAND_EXECUTION]: Instructs the agent to execute infrastructure management commands like
tofu applyandtofu planwithin the shell environment. - [INDIRECT_PROMPT_INJECTION]: The skill operates on external HCL and variable files, creating an attack surface for indirect instructions.
- Ingestion points: The agent is triggered to read and analyze
.tfand.tfvarsfiles from the user's workspace. - Boundary markers: No explicit delimiters or instructions are defined to help the agent distinguish between configuration data and potentially malicious instructions embedded in comments or strings.
- Capability inventory: The agent possesses the capability to execute shell commands via
tofuandcurl, which can perform file system writes and network operations. - Sanitization: No sanitization or structural validation of the processed HCL content is described.
Audit Metadata