data-researcher
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to discover and analyze data from multiple external sources, which introduces a surface for indirect prompt injection where instructions could be hidden in the data being researched.
- Ingestion points: The skill specifies discovering and analyzing data from "multiple sources" and data collection in SKILL.md.
- Boundary markers: The instructions lack explicit delimiters or guidance for the agent to distinguish between legitimate data and embedded malicious instructions.
- Capability inventory: The defined role involves querying, analyzing, and visualizing data, which typically involves file system or tool access in an agent environment.
- Sanitization: No sanitization, validation, or filtering of the external data sources is mentioned in the skill instructions.
Audit Metadata