nature-microbiology
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and formatting templates for the AI agent to follow when acting as a publication advisor. There are no scripts, binaries, or executable commands included.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided manuscripts, abstracts, and study descriptions. While this creates a surface for indirect prompt injection (where a user might include instructions in their manuscript to deceive the AI), the skill lacks any dangerous capabilities—such as network exfiltration tools, file-write permissions, or subprocess execution—that could be leveraged for malicious purposes.
- Ingestion points: User-provided manuscript content and study details.
- Boundary markers: Not explicitly defined in the instruction set.
- Capability inventory: No dangerous system or network capabilities are defined or requested in the skill frontmatter or body.
- Sanitization: None specified for input text.
Audit Metadata