byte-start
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks.
- Ingestion points: Step 3 of the workflow in SKILL.md uses a web search to retrieve data from external, untrusted sources (competitor sites, articles, app stores).
- Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to disregard any instructions found within the retrieved research data.
- Capability inventory: The skill is designed to perform network searches and write to the local filesystem (specifically the .byte-os/ directory and its markdown files).
- Sanitization: No sanitization, validation, or filtering of external content is defined before it is processed by the roles and recorded in project artifacts.
Audit Metadata