scientific-writing
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of academic documentation and reference materials. No scripts, shell commands, or unauthorized data access patterns were detected.\n- [NO_CODE]: This skill does not include or execute any code. It relies entirely on instructions and reference documents provided in Markdown format.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and revise user-provided manuscript text, creating a surface area for potential indirect injection.\n
- Ingestion points: User-supplied manuscript sections (abstract, methods, etc.) provided for writing or revision (SKILL.md).\n
- Boundary markers: Absent; there are no specific instructions or delimiters used to isolate user-provided content from the agent's core instructions.\n
- Capability inventory: The skill has no tool access, shell execution, or network writing capabilities, effectively neutralizing risks associated with injection.\n
- Sanitization: Absent; the instructions do not specify a process for validating or cleaning user-provided research text.
Audit Metadata