bento-multi-phase-plan
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and follow instructions from repository-specific files such as
AGENTS.md,CLAUDE.md, and local skill overlays located at.agents/bento/bento-multi-phase-plan.md. This creates a surface where external repository content can influence agent behavior. - Ingestion points: The agent is directed to read
AGENTS.md,CLAUDE.md, and.agents/bento/bento-multi-phase-plan.mdfrom the repository root. - Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from obeying malicious directives embedded within these repository-level files.
- Capability inventory: The skill focus is on planning and checklist generation, but it references other capabilities such as prototyping (
bento-prototype) and quality assurance (bento-qa), which may involve file system operations or test execution. - Sanitization: There are no explicit instructions for the agent to sanitize or validate the content of the repository-level instructions before adoption.
Audit Metadata