scientific-manuscript-review
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and a JSON rubric. No malicious patterns, obfuscation, or harmful commands were found.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process manuscripts and reviewer feedback which are external inputs. 1. Ingestion points: User-supplied manuscript drafts and feedback mentioned in SKILL.md. 2. Boundary markers: None present. 3. Capability inventory: Text analysis and generation only; no file-write, network-ops, or subprocess execution capabilities exist in the skill scripts. 4. Sanitization: No sanitization of user input is performed. Given the lack of dangerous capabilities, this surface is considered safe.
Audit Metadata