rk-quantum-network
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to resolve the active paper and project context from instructions contained within local files like
AGENTS.md. This design pattern allows external data to provide instructions to the agent, creating a surface for indirect prompt injection. - Ingestion points: The
Active papersection specifies reading instructions from the working directory andAGENTS.mdfiles. - Boundary markers: The skill does not provide specific delimiters or warnings to separate project-level instructions from the agent's core instructions.
- Capability inventory: The skill involves reading project files, copying simulator code, and generating network protocol reports.
- Sanitization: There is no instruction for the agent to sanitize or validate the content of the ingested project files.
Audit Metadata