bento-prototype
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and follow instructions from repository files such as
AGENTS.md,CLAUDE.md, and.agents/bento/bento-prototype.md. This creates a surface where malicious content within a repository could influence the agent's behavior. - Ingestion points: Reads
AGENTS.md,CLAUDE.md, and repo-root overlays inSKILL.md. - Boundary markers: None explicitly defined in the prompt instructions.
- Capability inventory: The agent is instructed to create files and execute scripts in a scratch directory.
- Sanitization: No specific sanitization or validation of the repo-level documentation is mentioned.
- [DYNAMIC_EXECUTION]: The primary function of the skill is to generate and execute small scripts or HTML/JS prototypes in an isolated directory. While this involves dynamic code generation, it is the intended purpose of the tool and is constrained to a 'scratch' environment.
Audit Metadata