capawesome-cli
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process various external data sources that could be used to influence the agent's behavior if they contained malicious content.
- Ingestion points: Project configuration files (
capawesome.config.json,package.json,.env), build/deployment logs, and AI-generated failure summaries (apps:builds:failure-summary). - Boundary markers: The instructions do not mandate the use of delimiters or specific safety warnings when the agent reads or presents data from these external sources.
- Capability inventory: The agent can execute numerous shell commands via the
@capawesome/cli, providing significant interaction with local files and remote cloud services. - Sanitization: There are no defined procedures for sanitizing or validating the content of project files before the agent uses them in command execution.
- [COMMAND_EXECUTION]: The skill is centered around the execution of shell commands using the Capawesome CLI tool to perform tasks like authentication, application management, and CI/CD operations.
Audit Metadata