fluentci-wasm-modules
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data that could contain malicious instructions.
- Ingestion points: The skill reads module manifests (fluentci-module.toml), SDK lockfiles, and source code entry points to configure modules.
- Boundary markers: The instructions do not define delimiters or specific warnings to the agent to ignore instructions embedded within these external files.
- Capability inventory: The skill uses the fluentci CLI to perform shell execution, file writing, and network operations (downloading dependencies and publishing artifacts).
- Sanitization: There is no mention of sanitizing or validating the contents of manifest or source files before they are used to influence the agent's execution of CLI commands.
- [COMMAND_EXECUTION]: The skill relies on shell commands through the fluentci CLI for tasks such as scaffolding (fluentci init), building, and running modules (fluentci run). These commands execute logic defined in WebAssembly components on the host system.
- [REMOTE_CODE_EXECUTION]: The skill supports the integration of remote code through dependency management. The command fluentci add math --git https://github.com/example/modules demonstrates the capability to fetch and link external Git-based code into the local execution environment.
- [EXTERNAL_DOWNLOADS]: The skill describes functionality for downloading modules from Git repositories and official registries to fulfill dependencies defined in the module manifest.
Audit Metadata