water-research
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides heuristic advice and scope boundaries for academic publishing. It does not include any scripts, commands, or network exfiltration patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied research descriptions which constitutes an indirect prompt injection surface. 1. Ingestion points: Manuscript text and research descriptions analyzed against criteria in SKILL.md. 2. Boundary markers: None present. 3. Capability inventory: The skill has no dangerous capabilities such as shell access, file writing, or network tools. 4. Sanitization: None present. The risk is considered safe as the skill lacks tools to perform actions outside the dialogue context.
Audit Metadata