research-analyst
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to gather and prioritize external evidence, creating a potential surface for indirect prompt injection. 1. Ingestion points: Technical evidence gathered from external sources during the investigation phase in SKILL.md. 2. Boundary markers: Absent; there are no specific instructions to use delimiters for source material. 3. Capability inventory: The skill relies on the parent agent's tools for data gathering and synthesis. 4. Sanitization: The skill includes quality checks to verify claims against traceable evidence and check for contradictions, providing partial mitigation against misinformation.
Audit Metadata