research-synthesizer
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted research data from multiple sources.
- Ingestion points: Data is ingested via placeholders in SKILL.md.
- Boundary markers: XML-style tags provide structure, but no instructions warn the agent to ignore instructions within the sources.
- Capability inventory: No tools, subprocesses, or network operations are present.
- Sanitization: No validation or filtering is applied to source content.
Audit Metadata