byte-deliver
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted content from multiple project files to generate handoff documentation and decide whether to start a development server.
- Ingestion points: Reads from .byte-os/ directory including logs, plans, and reviews as specified in SKILL.md.
- Boundary markers: No delimiters or instructions to ignore embedded commands are provided for the ingested data.
- Capability inventory: Capability to modify local files (.byte-os/DELIVERY.md, STATUS.md) and execute shell commands to start servers.
- Sanitization: The skill does not describe any validation or escaping of the ingested file content.
- [COMMAND_EXECUTION]: Instructions in SKILL.md direct the agent to initiate a local development server and provide local URLs, which involves executing system commands based on the inferred project requirements and metadata.
Audit Metadata