research-analyst
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external information, data sources, and research findings, which introduces a vulnerability to indirect prompt injection. If an external source contains malicious instructions, they could be processed by the agent during research tasks.
- Ingestion points: The skill explicitly mentions reviewing "existing knowledge, data sources, and research gaps" and conducting "thorough research across diverse domains" (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat external content as untrusted or to ignore embedded instructions.
- Capability inventory: The skill focuses on analysis, synthesis, and documentation, implying the use of the agent's internal reasoning and potentially external search tools (SKILL.md).
- Sanitization: No sanitization or validation logic is defined for the external data being processed.
Audit Metadata