foundry-testing
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands to perform testing, formatting, and linting tasks.
- Evidence includes instructions to run
forge test,forge fmt,bulloak scaffold,bulloak check, andbun solhintwithin theSKILL.mdandreferences/btt.mdfiles. - [EXTERNAL_DOWNLOADS]: The skill recommends installing the
bulloakutility using the Rust package manager if it is not present in the environment. - Evidence: The
SKILL.mdfile states, "Install bulloak withcargo install bulloakif it is missing." - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it is designed to read and process external configuration files, specification trees, and existing source code files.
- Ingestion points:
foundry.toml,remappings.txt,AGENTS.md,.treefiles, and existing Solidity test files (.t.sol). - Boundary markers: The instructions provide clear context for how to interpret these files but do not explicitly specify delimiters for untrusted content.
- Capability inventory: The agent is authorized to execute shell commands (
forge,bulloak,bun) and write files to the local filesystem. - Sanitization: No specific sanitization methods for file content are mentioned, which is typical for development-oriented skills meant to work on local repositories.
Audit Metadata