byte-build
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is build orchestration and plan execution, which involves reading local files and executing standard developer tools. No suspicious network activity, credential harvesting, or obfuscation was found.
- [PROMPT_INJECTION]: The skill ingests data from local plan and specification files, which represents a surface for indirect prompt injection. However, this is consistent with the skill's primary purpose of executing user-defined plans.
- Ingestion points: .byte-os/plans/*.plan.md, .byte-os/PRODUCT_SPEC.md, .byte-os/TECH_SPEC.md, .byte-os/UX_SPEC.md, .byte-os/OKRS.md in SKILL.md.
- Boundary markers: None explicitly defined.
- Capability inventory: Subprocess execution (tests, linters, builds), file system modifications, and delegation to subagents in SKILL.md.
- Sanitization: Not explicitly implemented in the skill instructions.
Audit Metadata