paper-review
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's logic is confined to document analysis and academic critiquing. It does not attempt to access credentials, modify the file system, or establish persistence.
- [PROMPT_INJECTION]: Although the skill processes external papers (untrusted data), it lacks high-privilege capabilities that would make indirect prompt injection a significant risk.
- Ingestion points: Manuscript drafts and final submissions are processed in the review workflow.
- Boundary markers: Instructions do not specify delimiters to isolate the manuscript text.
- Capability inventory: The skill utilizes a WebSearch tool for literature review.
- Sanitization: No sanitization logic for the ingested manuscript content is included in the skill definition.
Audit Metadata