byte-iterate
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection due to its core functionality of processing untrusted data.
- Ingestion points: The skill explicitly reads content from
.byte-os/reviews/*.mdand.byte-os/users/*.md, which are intended to store external feedback and user-provided materials. - Boundary markers: The instructions lack clear delimiters or "ignore embedded instructions" directives to prevent the agent from being influenced by malicious commands hidden within the feedback files.
- Capability inventory: The skill possesses file-write capabilities (to
.byte-os/iterations/,.byte-os/ROADMAP.md, and.byte-os/STATUS.md) and instructs the agent to invoke thebyte-buildbehavior for execution, which may involve code generation or system changes. - Sanitization: No sanitization or validation logic is defined for the external data before it is incorporated into the iteration planning and execution steps.
Audit Metadata