byte-research
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 due to its core functionality of ingesting and processing untrusted data from the web.\n
- Ingestion points: The agent is instructed to browse external product pages, documentation, pricing pages, and reviews as part of its research workflow.\n
- Boundary markers: No explicit delimiters or instructions are provided to help the agent distinguish between external data and its own system instructions, nor to ignore instructions within the web content.\n
- Capability inventory: The agent has permissions to read local context files (e.g.,
.byte-os/BYTE.md,ROADMAP.md) and write new artifacts to the.byte-os/directory (e.g.,RESEARCH.md,DECISIONS.md).\n - Sanitization: There is no evidence of sanitization or validation of the data retrieved from the web before it is incorporated into the agent's context or stored in files.
Audit Metadata