byte-shape
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's functionality is confined to reading and writing local project documentation, posing no threat to system integrity or data privacy.
- [PROMPT_INJECTION]: The skill ingests untrusted data from various local files, creating an indirect prompt injection surface.
- Ingestion points: Reads multiple project files including .byte-os/RESEARCH.md and .byte-os/COMPETITORS.md (SKILL.md).
- Boundary markers: Absent; no delimiters are used to wrap external content or warn the agent.
- Capability inventory: Capabilities are limited to writing markdown files within the local .byte-os/ directory; no subprocess execution or network operations are involved.
- Sanitization: Absent; no validation is performed on the ingested documentation content.
Audit Metadata