skills/brycewang-stanford/awesome-journal-skills/journal-of-clinical-investigation/Gen Agent Trust Hub
journal-of-clinical-investigation
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a domain-specific instruction set for academic publishing. It does not contain any evidence of credential theft, remote code execution, persistence mechanisms, or obfuscation.
- [INDIRECT_PROMPT_INJECTION]: The skill processes manuscript data provided by users, creating a surface for potential indirect prompt injection attacks. However, the skill's capabilities are limited to text generation and guidance, with no access to dangerous tools, file system modifications, or sensitive network operations.
- Ingestion points: Processes manuscript text, data summaries, and author descriptions provided during the agent interaction.
- Boundary markers: No specific delimiters or "ignore instructions" wrappers are provided for the user input.
- Capability inventory: Limited to providing textual feedback and venue re-routing advice. The skill references local resources (source-basis.md) for its own configuration but does not request hazardous tool access.
- Sanitization: No data validation or sanitization of user-provided manuscript content is performed.
Audit Metadata