scientific-manuscript-review
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional markdown and JSON rubric files intended for document review. It contains no executable code, shell commands, or network-based data transfer.
- [INDIRECT_PROMPT_INJECTION]: The skill operates on untrusted user-provided manuscript drafts.
- Ingestion points: Manuscript drafts input (SKILL.md).
- Boundary markers: No delimiters or ignore instructions are present for the input text.
- Capability inventory: Restricted to text editing and commentary; no high-privilege tools or dangerous capabilities are requested.
- Sanitization: No input validation is performed on the manuscript content.
Audit Metadata