research
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious instructions, obfuscation, or unauthorized access patterns were found.
- [PROMPT_INJECTION]: The skill processes external content (primary sources, documentation, and source code) which presents an inherent risk of indirect prompt injection. This is a characteristic of research-focused agents and is managed by the underlying model's safety guardrails. Ingestion points: external documentation, source code, and specs (SKILL.md). Boundary markers: absent. Capability inventory: writes Markdown files to the local repository. Sanitization: absent.
Audit Metadata