manta-cli
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to run
MANTA skills get manta-clito load a "full guide" and follow its instructions. This creates an indirect prompt injection surface where the agent may process and obey instructions returned by a tool command (Category 8c). - [COMMAND_EXECUTION]: The skill resolves a local executable based on environment variables (
MANTA_CLI_COMMAND,MANTA_DEV_REPO_ROOT) and executes it to interact with the system. While this is the intended functionality, it relies on the integrity of the environment-defined binary.
Audit Metadata