journal-of-clinical-oncology
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured guidance for manuscript preparation and venue selection. It does not contain any code, network exfiltration patterns, or attempts to bypass safety filters. All instructions are context-appropriate for its stated purpose as a medical publishing aid.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing user-provided manuscript text and results from external web searches (SKILL.md). This represents a standard surface for indirect prompt injection common to all LLM-based guidance skills. However, the skill does not possess high-risk capabilities such as file system writing, dynamic code execution, or network exfiltration of sensitive data, which significantly limits the potential for exploitation.
- Ingestion points: User manuscripts and live web search results.
- Boundary markers: None present.
- Capability inventory: Information retrieval, text generation, and venue selection.
- Sanitization: None present.
Audit Metadata