byte-next
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it uses the content of local project files to determine its next actions. An attacker who can modify files like STATUS.md or PRODUCT_SPEC.md could potentially influence the agent's behavior.
- Ingestion points: The skill reads from .byte-os/STATUS.md, .byte-os/PRODUCT_SPEC.md, and .byte-os/OKRS.md.
- Boundary markers: No delimiters are present to separate untrusted data from system instructions.
- Capability inventory: The skill can write, review, and refactor code, and execute other workflow commands.
- Sanitization: There is no logic to sanitize or validate the content of the project files before processing.
Audit Metadata