cross-tool-research
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define data ingestion points from external connectors such as alerts, logs, and documents within SKILL.md. No specific boundary markers or sanitization procedures are defined. However, the capability inventory is focused on research and correlation, and the instructions promote safety by requiring the agent to distinguish evidence from inference.
- [NO_CODE]: The skill is entirely instructional and does not include any executable scripts, command-line operations, or external software dependencies.
Audit Metadata